© 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. 9-LLAMASCOPE-RES-131K
    11. 94354
    Prev
    Next
    INDEX
    Explanations

    usages of the word "mouse" in relation to interactions or actions involving user interfaces

    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
    /dis
    -0.07
    shaw
    -0.07
    ÑģÑĭлки
    -0.07
    kovi
    -0.07
    ãģıãĤĵ
    -0.07
    grese
    -0.07
    uter
    -0.07
    zos
    -0.07
    asurer
    -0.07
    shal
    -0.07
    POSITIVE LOGITS
    walk
    0.06
     punk
    0.06
    /email
    0.06
    gun
    0.06
    indy
    0.05
    uh
    0.05
    arrants
    0.05
     Punk
    0.05
    cano
    0.05
    raki
    0.05
    Activations Density 0.003%

    No Known Activations