© 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. 72088
    Prev
    Next
    INDEX
    Explanations

    coding-related constructs and terms

    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
    inton
    -0.07
    ippo
    -0.07
    oden
    -0.06
    iar
    -0.06
    NECT
    -0.06
    inate
    -0.06
    owl
    -0.06
    .setPrototypeOf
    -0.06
    iyim
    -0.06
    .mixin
    -0.06
    POSITIVE LOGITS
    /commons
    0.07
    aldi
    0.07
     Commons
    0.07
    nob
    0.07
    جÙħÙĪع
    0.06
    tega
    0.06
    é¡ĶãĤĴ
    0.06
    irt
    0.06
    urovision
    0.06
    irector
    0.06
    Activations Density 0.020%

    No Known Activations