© 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. 56378
    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
     Finch
    -0.06
     Ferr
    -0.06
     cult
    -0.06
    説
    -0.06
    .asp
    -0.05
    chw
    -0.05
    .fun
    -0.05
     Agr
    -0.05
    408
    -0.05
    .inflate
    -0.05
    POSITIVE LOGITS
     Indigenous
    0.09
     Native
    0.09
    .Native
    0.08
    Apache
    0.08
     Apache
    0.08
     Clan
    0.07
     Aboriginal
    0.07
     clan
    0.07
    Native
    0.07
     ance
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.