© 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. 80107
    Prev
    Next
    INDEX
    Explanations

    questions or statements that express uncertainty or inquiry

    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
    ÄIJT
    -0.08
    .Binary
    -0.07
    ÏĦεÏģ
    -0.07
    uil
    -0.07
    jadi
    -0.07
     hete
    -0.07
     jezd
    -0.07
    .sourceforge
    -0.07
    нима
    -0.07
    otros
    -0.06
    POSITIVE LOGITS
     recent
    0.09
     recently
    0.08
     article
    0.07
     guest
    0.07
    immel
    0.07
     lately
    0.06
     Article
    0.06
    recent
    0.06
     Recent
    0.06
     ARTICLE
    0.06
    Activations Density 0.074%

    No Known Activations