© 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. 87102
    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
    nero
    -0.07
    ieri
    -0.07
    entine
    -0.07
    ope
    -0.07
    eniz
    -0.07
    nte
    -0.07
    ntl
    -0.07
    Ø·Ùĩ
    -0.07
    inae
    -0.06
    uros
    -0.06
    POSITIVE LOGITS
    Round
    0.06
    dag
    0.06
    jal
    0.06
    lund
    0.06
     round
    0.06
     lightweight
    0.06
    898
    0.06
    _qos
    0.06
    fcn
    0.05
    ÑĢид
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.