© 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. 86315
    Prev
    Next
    INDEX
    Explanations

    articles such as "the" and other determiner associated tokens in the text

    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
    Ñīин
    -0.07
    幸
    -0.07
    rets
    -0.07
    oretical
    -0.07
     $__
    -0.07
    ãĤĮãģ©
    -0.07
    oggles
    -0.07
    eno
    -0.07
    uen
    -0.07
    _EXTERN
    -0.07
    POSITIVE LOGITS
     there
    0.09
     unlike
    0.08
     otherwise
    0.07
     majority
    0.07
     it
    0.07
    there
    0.07
     they
    0.06
     only
    0.06
     stakes
    0.06
    765
    0.06
    Activations Density 0.043%

    No Known Activations