© 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. 54383
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Jose."

    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
    erse
    -0.09
    nee
    -0.07
    oust
    -0.07
    zeitig
    -0.07
    aiser
    -0.06
    ruz
    -0.06
    .ts
    -0.06
    _traits
    -0.06
    ring
    -0.06
    resp
    -0.06
    POSITIVE LOGITS
    enthal
    0.07
    ardy
    0.07
    pth
    0.07
    elyn
    0.07
    eph
    0.07
    okit
    0.07
    ita
    0.06
    phin
    0.06
    affles
    0.06
    urette
    0.06
    Activations Density 0.006%

    No Known Activations