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

    Neuronpedia

    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. 129399
    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
     Gund
    -0.07
    quires
    -0.06
    åŃĿ
    -0.06
     Bender
    -0.06
    -0.06
    ucky
    -0.06
    ÑĢабоÑĤ
    -0.06
    IRT
    -0.06
     recently
    -0.06
    @js
    -0.06
    POSITIVE LOGITS
    idl
    0.08
    akis
    0.07
    stype
    0.07
     наÑıв
    0.07
    gos
    0.07
    ipse
    0.07
    engl
    0.06
    wl
    0.06
    ipple
    0.06
    indr
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.