© 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. 125684
    Prev
    Next
    INDEX
    Explanations

    references to getting more information or instructions

    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
    gnore
    -0.07
    िह
    -0.07
     Notices
    -0.07
    ă
    -0.06
    ลà¸ĩ
    -0.06
    cker
    -0.06
    reich
    -0.06
     ìĸ¸
    -0.06
    одаÑĢ
    -0.06
     sát
    -0.06
    POSITIVE LOGITS
     official
    0.07
     website
    0.06
    bef
    0.06
     Mes
    0.06
     HERE
    0.06
    ermo
    0.06
    opens
    0.06
     Lars
    0.06
     Bryant
    0.06
    lags
    0.06
    Activations Density 0.021%

    No Known Activations