© 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. 76491
    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
    Ìģ
    -0.07
    ventus
    -0.07
    iversit
    -0.06
    åħ¥ãĤĬ
    -0.06
     __("
    -0.06
    ãĥģãĥ¥
    -0.06
     Karlov
    -0.06
    ainen
    -0.06
    857
    -0.06
    mdb
    -0.06
    POSITIVE LOGITS
     arous
    0.07
    /xhtml
    0.06
     Myst
    0.06
     ê´Ģíķľ
    0.06
    unya
    0.05
     envis
    0.05
    MeasureSpec
    0.05
    ACS
    0.05
    ibu
    0.05
    argas
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.