© 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 EvalsExportsAPI 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. 78422
    Prev
    Next
    INDEX
    Explanations

    references to web programming and support for Internet Explorer

    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
    ledon
    -0.07
    lotte
    -0.07
    alars
    -0.07
    tons
    -0.07
    elters
    -0.07
    yro
    -0.07
    strup
    -0.07
    occan
    -0.07
    elerine
    -0.07
    ocre
    -0.07
    POSITIVE LOGITS
    ฤษ
    0.06
     *----------------------------------------------------------------
    0.06
     Ferguson
    0.06
    κÎŃ
    0.06
    ÑĢÑĥп
    0.06
    íĻĺ
    0.06
    κε
    0.06
    nr
    0.06
    907
    0.06
     PhpStorm
    0.05
    Activations Density 0.000%

    No Known Activations