© 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. 124768
    Prev
    Next
    INDEX
    Explanations

    references to doors and entryways

    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
    ÙĪئ
    -0.08
    ged
    -0.07
    kle
    -0.07
    ency
    -0.07
    enko
    -0.07
    ging
    -0.07
    furt
    -0.07
    mons
    -0.06
    imoto
    -0.06
    uran
    -0.06
    POSITIVE LOGITS
    ways
    0.12
    bell
    0.11
    keeper
    0.08
    frame
    0.08
    steps
    0.07
    lier
    0.07
    erce
    0.07
    ải
    0.07
    -door
    0.07
    anut
    0.07
    Activations Density 0.013%

    No Known Activations