© 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. 41467
    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
    edla
    -0.06
    meg
    -0.06
    enso
    -0.06
     Lyon
    -0.06
    室
    -0.06
     Mah
    -0.06
    .vx
    -0.06
    mah
    -0.06
    -0.06
    [args
    -0.06
    POSITIVE LOGITS
    ibil
    0.08
    iaux
    0.07
    ħ§
    0.07
     Await
    0.07
    pector
    0.06
    oplevel
    0.06
    lingen
    0.06
    mere
    0.06
    .qual
    0.06
     Tato
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.