© 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. 106785
    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
    opal
    -0.07
    éĶĭ
    -0.07
    UPLE
    -0.07
    ιÏĥ
    -0.07
    ILLED
    -0.06
    alama
    -0.06
    acket
    -0.06
    errer
    -0.06
    babel
    -0.06
    alis
    -0.06
    POSITIVE LOGITS
     detailed
    0.08
    485
    0.07
     ArgumentOutOfRangeException
    0.06
    Detailed
    0.06
     иÑģÑĤоÑĢии
    0.06
    989
    0.06
     Ther
    0.06
     detail
    0.06
     Detailed
    0.06
    νοÏį
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.