© 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. 55131
    Prev
    Next
    INDEX
    Explanations

    sections of code or text related to web resources or hyperlinks

    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
    iyat
    -0.07
    ollo
    -0.07
    ìļ°
    -0.06
    alis
    -0.06
    arend
    -0.06
     kicker
    -0.06
    empor
    -0.06
     çŃ
    -0.06
    icularly
    -0.06
    Ìģ
    -0.06
    POSITIVE LOGITS
    éĩı
    0.06
    eryl
    0.06
    º
    0.06
     Hastings
    0.06
    oose
    0.06
    iado
    0.06
    ynamo
    0.06
     Ding
    0.06
     Dut
    0.06
    chants
    0.06
    Activations Density 0.000%

    No Known Activations