© 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. 18160
    Prev
    Next
    INDEX
    Explanations

    elements of coding or programming syntax related to functions and parameters

    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
    raç
    -0.07
    afia
    -0.07
    hus
    -0.06
    ushi
    -0.06
    acco
    -0.06
     (
    -0.06
    nan
    -0.06
    nob
    -0.06
    isku
    -0.06
    icari
    -0.06
    POSITIVE LOGITS
    olas
    0.06
    ãģįãģŁ
    0.06
    ij
    0.06
    errupt
    0.06
    |array
    0.06
    adoo
    0.06
    ене
    0.06
    iver
    0.06
    opleft
    0.06
    stown
    0.06
    Activations Density 0.022%

    No Known Activations