© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 91876
    Prev
    Next
    INDEX
    Explanations

    elements related to programming or scripting 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
    opak
    -0.07
     Boeh
    -0.06
    etik
    -0.06
    EventManager
    -0.06
    éĸ
    -0.06
     rip
    -0.06
     SMTP
    -0.06
     Threshold
    -0.06
     banka
    -0.06
    vis
    -0.05
    POSITIVE LOGITS
    emez
    0.08
    skirts
    0.07
    ogenerated
    0.07
    setParameter
    0.07
    ishi
    0.07
    ascus
    0.07
    èįī
    0.07
    plet
    0.07
    /lic
    0.06
     strokeLine
    0.06
    Activations Density 0.014%

    No Known Activations