© 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. 117651
    Prev
    Next
    INDEX
    Explanations

    identifiers and references to variables or functions in 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
    PointerException
    -0.07
    /******/
    -0.06
    fax
    -0.06
    BuilderInterface
    -0.06
    plugin
    -0.06
    ابت
    -0.06
    ourse
    -0.06
    ÙĪÙĤت
    -0.06
    .mods
    -0.06
     GUIDE
    -0.06
    POSITIVE LOGITS
    kee
    0.07
    .png
    0.06
    sword
    0.06
    perc
    0.06
    elts
    0.06
    uner
    0.06
    icals
    0.06
    illance
    0.06
    .jpg
    0.06
    ãģ¤ãģ®
    0.06
    Activations Density 0.134%

    No Known Activations