© 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. 125415
    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
    aea
    -0.07
     plac
    -0.06
     Ziel
    -0.06
     squ
    -0.06
     #
    -0.06
    ardo
    -0.06
     mur
    -0.06
     *
    -0.06
     
    -0.06
     +
    -0.06
    POSITIVE LOGITS
     tolua
    0.09
     addCriterion
    0.08
     defaultManager
    0.08
    ixel
    0.07
    RecognitionException
    0.07
    .Guna
    0.07
    HeaderCode
    0.07
    ausible
    0.07
    .raises
    0.07
    Cheers
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.