© 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 EvalsExportsinterp-engineNEWAPI 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. 121168
    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
     Hindered
    -0.08
    illez
    -0.08
    yonel
    -0.08
    oen
    -0.07
    \Bridge
    -0.07
    ienie
    -0.07
    ensch
    -0.07
    AdapterFactory
    -0.07
    .Experimental
    -0.07
    inesis
    -0.07
    POSITIVE LOGITS
    ãĤįãģĨ
    0.07
    uge
    0.06
    ãĥįãĥ«
    0.06
    kee
    0.06
    Ã
    0.06
    IGO
    0.06
    ãĥ¬ãĥĥãĥĪ
    0.06
    terminal
    0.06
    :last
    0.05
    viron
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.