© 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. 94164
    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
    conto
    -0.08
    =end
    -0.07
    :convert
    -0.07
    bsolute
    -0.07
    дина
    -0.07
    ellow
    -0.07
    azar
    -0.07
    Swagger
    -0.07
    mania
    -0.07
     Eb
    -0.07
    POSITIVE LOGITS
     Lect
    0.06
    stown
    0.06
     spam
    0.06
     defenses
    0.06
    anko
    0.06
     vener
    0.06
     Traverse
    0.06
     à¹Ĩ
    0.05
     Mature
    0.05
     labeling
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.