© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 25-LLAMASCOPE-RES-32K
    11. 32268
    Prev
    Next
    INDEX
    Explanations

    references to the term "lev" and its various forms, indicating a focus on topics related to legal or structured frameworks, possibly including legislation or guidelines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the prefix or root "Lev" in proper nouns and technical terms (especially names like Leviticus, Levantine, Levowitz, and words related to levitation/levity).

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    words containing the substring “lev,” especially at the start of a word.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     {{--<
    -0.17
    ól
    -0.16
    jekt
    -0.15
    oms
    -0.15
    .nih
    -0.14
    iff
    -0.14
    çī§
    -0.14
    oles
    -0.14
    assen
    -0.14
     weg
    -0.14
    POSITIVE LOGITS
     lev
    0.24
    itation
    0.23
    itating
    0.23
    antine
    0.23
     Lev
    0.22
    itated
    0.21
    itate
    0.21
    elling
    0.21
    ellers
    0.19
    itical
    0.19
    Activations Density 0.011%

    No Known Activations