Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 82887
    Prev
    Next
    INDEX
    Explanations

    terms related to configuration and programming concepts

    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
     BusinessException
    -0.07
     stitch
    -0.07
    anus
    -0.07
    jab
    -0.07
     ServiceException
    -0.07
    imoto
    -0.06
     stripe
    -0.06
    lint
    -0.06
    raya
    -0.06
    pez
    -0.06
    POSITIVE LOGITS
    /cop
    0.07
    939
    0.07
    QUEST
    0.06
    _Callback
    0.06
    AMPL
    0.06
     QUEST
    0.06
    ãģ£ãģ±
    0.06
    -shop
    0.06
    Occurrences
    0.06
     placer
    0.06
    Activations Density 0.026%

    No Known Activations