© 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. 128951
    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
    umi
    -0.06
    esModule
    -0.06
    ,[],
    -0.06
    lero
    -0.06
    .Framework
    -0.06
    åĥ
    -0.06
    uParam
    -0.06
    ryfall
    -0.06
    365
    -0.05
     seper
    -0.05
    POSITIVE LOGITS
    abbrev
    0.08
    eneg
    0.07
    .yahoo
    0.07
    tement
    0.07
    ãģ»ãģĨ
    0.07
     horse
    0.07
    quine
    0.07
    -wow
    0.07
    uby
    0.06
     Horse
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.