© 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. 1-LLAMASCOPE-RES-32K
    11. 16114
    Prev
    Next
    INDEX
    Explanations

    plural nouns, particularly those ending in 'er' or 'ers'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 1-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    phere
    -0.16
    beck
    -0.16
    arro
    -0.15
    uir
    -0.15
    ajs
    -0.15
    ton
    -0.14
    .onView
    -0.14
    иной
    -0.14
    ((-
    -0.14
    خت
    -0.14
    POSITIVE LOGITS
    repid
    0.17
    iego
    0.17
    emiah
    0.14
    .dylib
    0.14
    owied
    0.14
    нед
    0.14
    emo
    0.14
    oulouse
    0.14
    etails
    0.14
    çŁ¥
    0.13
    Activations Density 0.101%

    No Known Activations