© 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. 84213
    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
    agan
    -0.06
    meni
    -0.06
    eper
    -0.06
    μÏĨ
    -0.06
     Sabb
    -0.06
    avanaugh
    -0.06
     bumped
    -0.06
    lopen
    -0.06
    elas
    -0.06
    AppState
    -0.06
    POSITIVE LOGITS
    (AF
    0.07
     çĬ
    0.07
     Kauf
    0.07
    elper
    0.06
    .cent
    0.06
     mans
    0.06
    ships
    0.06
    .Ultra
    0.06
    etch
    0.06
    ude
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.