© 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. 88850
    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
    riet
    -0.08
    259
    -0.07
    ULE
    -0.07
    unami
    -0.07
    foon
    -0.07
    eczy
    -0.06
    phoon
    -0.06
     Alvarez
    -0.06
     Schmidt
    -0.06
    λει
    -0.06
    POSITIVE LOGITS
     muzzle
    0.08
    eno
    0.07
     mange
    0.06
     Toy
    0.06
     paw
    0.06
    lanma
    0.06
    dba
    0.06
    inois
    0.06
     piv
    0.06
    GD
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.