© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 60815
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    tics
    -0.06
     colle
    -0.06
    ãĢĤ↵↵↵↵↵↵
    -0.06
    laughter
    -0.06
    stry
    -0.06
    opens
    -0.06
     пок
    -0.06
    hti
    -0.06
    ienia
    -0.06
    ymes
    -0.06
    POSITIVE LOGITS
     probs
    0.07
    847
    0.06
    andel
    0.06
    976
    0.06
    aleb
    0.06
    ambi
    0.06
    λιά
    0.06
    .Term
    0.06
    оза
    0.06
    Started
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.