© 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. 40679
    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
     Rever
    -0.07
    rary
    -0.06
    ARGER
    -0.06
    ommen
    -0.06
    riba
    -0.06
     nữa
    -0.06
    Å©
    -0.06
    angkan
    -0.06
    cai
    -0.06
    ocused
    -0.06
    POSITIVE LOGITS
    Ùģت
    0.07
    auth
    0.06
     leadership
    0.06
     hypoth
    0.06
    endance
    0.06
    zel
    0.06
    agem
    0.06
    /opt
    0.06
    osal
    0.06
     Statements
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.