© 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. 15-LLAMASCOPE-RES-131K
    11. 87885
    Prev
    Next
    INDEX
    Explanations

    references to scientific concepts and biological processes related to mosquitoes

    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
    836
    -0.07
    atsby
    -0.06
    gren
    -0.06
    uchar
    -0.06
    ikat
    -0.06
     nucle
    -0.06
    egend
    -0.06
     carg
    -0.06
    ycz
    -0.06
    lop
    -0.06
    POSITIVE LOGITS
     Suites
    0.07
     manip
    0.07
    ecd
    0.07
    .digest
    0.07
     conv
    0.07
    ItemSelectedListener
    0.06
    $__
    0.06
     rang
    0.06
    Å¡ak
    0.06
    akah
    0.06
    Activations Density 0.003%

    No Known Activations