© 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. 119573
    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
    utin
    -0.07
    ë¶
    -0.06
     Beckham
    -0.06
    ulin
    -0.06
    illis
    -0.06
    ç·
    -0.06
     PREF
    -0.06
     ÙĪØ§Ø¨
    -0.06
     Thema
    -0.06
     fringe
    -0.05
    POSITIVE LOGITS
     togg
    0.07
    olean
    0.07
    rike
    0.07
    .ColumnName
    0.07
     fucking
    0.07
    оÑī
    0.06
    usra
    0.06
    ingleton
    0.06
    .scalablytyped
    0.06
    dana
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.