© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 106599
    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
    ackets
    -0.08
    ãĥ³ãĥĨ
    -0.08
    lü
    -0.07
    ãģ®ãģłãĤįãģĨ
    -0.07
    etik
    -0.07
    omba
    -0.07
    ãĤ¯ãĥ©ãĥĸ
    -0.07
    edb
    -0.07
    Manip
    -0.06
    \Tests
    -0.06
    POSITIVE LOGITS
     thing
    0.09
     lots
    0.09
     stuff
    0.08
    thing
    0.08
     things
    0.08
     kinda
    0.07
    our
    0.07
    Thing
    0.07
     kind
    0.07
     really
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.