© 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. 124372
    Prev
    Next
    INDEX
    Explanations

    occurrences of the token "::" associated with programming or code structure

    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
    nie
    -0.08
    InputDialog
    -0.08
    acad
    -0.07
     McA
    -0.07
     tox
    -0.06
    Schedulers
    -0.06
    виж
    -0.06
    urdy
    -0.06
    ĥĿ
    -0.06
    ằm
    -0.06
    POSITIVE LOGITS
    npos
    0.07
    orra
    0.07
    mouseenter
    0.07
    анÑĸÑĤ
    0.06
    koli
    0.06
     Zust
    0.06
    ůj
    0.06
    -addon
    0.06
    YLeaf
    0.06
    inand
    0.06
    Activations Density 0.007%

    No Known Activations