© 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. 86399
    Prev
    Next
    INDEX
    Explanations

    components related to calls to action or directives addressing the reader

    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
    .sms
    -0.07
     sund
    -0.07
    ace
    -0.07
    аÑĤкÑĥ
    -0.07
     *,↵
    -0.06
    /current
    -0.06
    (*)
    -0.06
    atre
    -0.06
    gee
    -0.06
    iff
    -0.06
    POSITIVE LOGITS
    Ħ
    0.07
     Keywords
    0.07
    eltas
    0.07
     ngữ
    0.07
    527
    0.07
    onte
    0.07
    رÙĪد
    0.07
    elt
    0.07
    .tintColor
    0.07
     doby
    0.06
    Activations Density 0.052%

    No Known Activations