© 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. 74782
    Prev
    Next
    INDEX
    Explanations

    adverbs indicating frequency or likelihood

    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
    strup
    -0.07
    reich
    -0.07
    ÑĢÑı
    -0.06
     Gone
    -0.06
    ÑĢан
    -0.06
    ırak
    -0.06
    stime
    -0.06
    775
    -0.06
    267
    -0.06
    137
    -0.06
    POSITIVE LOGITS
     very
    0.07
     highly
    0.07
    -too
    0.06
    -to
    0.06
    -for
    0.06
     familiar
    0.06
     non
    0.06
    ance
    0.06
    anced
    0.06
    urer
    0.06
    Activations Density 0.033%

    No Known Activations