© 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. 76733
    Prev
    Next
    INDEX
    Explanations

    terms related to specific classifications and standards

    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
    usercontent
    -0.07
     mastur
    -0.07
    èħIJ
    -0.07
    ë¡ł
    -0.07
    /frontend
    -0.07
    QN
    -0.07
    tsy
    -0.07
     meis
    -0.07
    isy
    -0.06
    à¹Ĩ
    -0.06
    POSITIVE LOGITS
     behalf
    0.08
    ATEGORIES
    0.07
     category
    0.07
    -equipped
    0.06
    anza
    0.06
    lee
    0.06
    enting
    0.06
     Regards
    0.06
    ColumnsMode
    0.06
    _SUPPORTED
    0.05
    Activations Density 0.097%

    No Known Activations