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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 3239
    Prev
    Next
    INDEX
    Explanations

    mentions of files and file-related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ensi
    -0.07
    ifu
    -0.07
    ransition
    -0.07
    eree
    -0.07
    otate
    -0.07
    ecycle
    -0.07
    amerate
    -0.07
    oningen
    -0.07
    ood
    -0.06
    /inet
    -0.06
    POSITIVE LOGITS
     Zwe
    0.08
     Nas
    0.06
    uitka
    0.06
    ³
    0.06
    eneric
    0.06
    \<
    0.06
     Gä
    0.06
    yat
    0.06
    FILE
    0.06
    iced
    0.06
    Activations Density 0.001%

    No Known Activations