© 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. 40669
    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
    earn
    -0.07
    isine
    -0.06
     whole
    -0.06
    (Parser
    -0.06
     amongst
    -0.06
    .ct
    -0.06
    ç´¯
    -0.06
     itself
    -0.06
    aleza
    -0.06
    onus
    -0.05
    POSITIVE LOGITS
    cheng
    0.07
    IfNeeded
    0.07
    odem
    0.07
    اگر
    0.07
     Analog
    0.07
    icorn
    0.06
    plusplus
    0.06
    dog
    0.06
    clamation
    0.06
     adultes
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.