© 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. 62077
    Prev
    Next
    INDEX
    Explanations

    function calls related to adding and removing elements or attributes in a programming context

    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
    ippet
    -0.07
    ogl
    -0.06
    coni
    -0.06
    asp
    -0.06
    orry
    -0.06
    ettings
    -0.06
    füg
    -0.06
    zh
    -0.06
    orrect
    -0.06
    odyn
    -0.06
    POSITIVE LOGITS
    endum
    0.10
    itionally
    0.09
    ITIONAL
    0.08
    ition
    0.07
    oned
    0.07
    itional
    0.06
    urga
    0.06
    ë²Į
    0.06
    /remove
    0.06
    abbo
    0.06
    Activations Density 0.015%

    No Known Activations