© 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. 17352
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or identifiers related to "Dul."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    istol
    -0.18
    ccak
    -0.15
    iros
    -0.15
    ylon
    -0.15
    etler
    -0.15
    omanip
    -0.15
    iya
    -0.14
    à¸ĩ
    -0.14
    elry
    -0.14
    rin
    -0.14
    POSITIVE LOGITS
    uth
    0.22
    oxetine
    0.18
    UTH
    0.17
    quer
    0.17
    wich
    0.17
     Dul
    0.15
     dul
    0.15
    les
    0.15
    ces
    0.14
    enses
    0.14
    Activations Density 0.003%

    No Known Activations