© 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. 57133
    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
    ç»ĩ
    -0.08
     dilig
    -0.07
    engl
    -0.07
    Bindings
    -0.07
    /browse
    -0.06
    .Extension
    -0.06
    radan
    -0.06
    EMPL
    -0.06
    .cms
    -0.06
    Ùİس
    -0.06
    POSITIVE LOGITS
     recieved
    0.07
    hed
    0.07
    ppard
    0.06
    ìĭł
    0.06
    tere
    0.06
    pled
    0.06
    oub
    0.06
     tent
    0.06
    ende
    0.06
    _SY
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.