© 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 EvalsExportsinterp-engineNEWAPI 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. 105458
    Prev
    Next
    INDEX
    Explanations

    structural elements or delimiters in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    евеÑĢ
    -0.07
    cht
    -0.07
    oog
    -0.07
    peria
    -0.07
    unma
    -0.07
    arrants
    -0.07
    eczy
    -0.07
    zion
    -0.06
    ยà¸ĩ
    -0.06
    ugo
    -0.06
    POSITIVE LOGITS
    ote
    0.06
     succession
    0.06
     kin
    0.06
    ãĥªãĤ¢
    0.06
    776
    0.05
    etas
    0.05
     åĬ
    0.05
    ((__
    0.05
     Lonely
    0.05
    oyal
    0.05
    Activations Density 0.000%

    No Known Activations