© 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. 58486
    Prev
    Next
    INDEX
    Explanations

    references to locations or contextual settings

    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
     Holl
    -0.09
    ogne
    -0.07
    xac
    -0.07
    alley
    -0.06
    ä¸Ģä¸ĭ
    -0.06
    ats
    -0.06
     olmaz
    -0.06
    ocab
    -0.06
    oph
    -0.06
    okens
    -0.06
    POSITIVE LOGITS
    sembl
    0.08
    orative
    0.08
    stå
    0.07
    üstü
    0.07
    //*[
    0.07
    anners
    0.07
    yling
    0.06
    nid
    0.06
    verter
    0.06
    Matchers
    0.06
    Activations Density 0.003%

    No Known Activations