© 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. 41461
    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
    uset
    -0.08
    ictim
    -0.08
    oÅĻ
    -0.07
    uars
    -0.07
    YRO
    -0.07
    linger
    -0.07
    ÅĻit
    -0.07
    iros
    -0.07
    moid
    -0.07
    utzer
    -0.07
    POSITIVE LOGITS
    538
    0.06
    ink
    0.06
    -answer
    0.05
    -
    0.05
    antar
    0.05
     Collins
    0.05
    angu
    0.05
     ver
    0.05
    ordin
    0.05
    yc
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.