© 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. 18200
    Prev
    Next
    INDEX
    Explanations

    the occurrence of the word "Be" in various contexts

    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
    pane
    -0.07
    recht
    -0.07
    ми
    -0.07
    ships
    -0.07
    li
    -0.07
    riba
    -0.07
    most
    -0.07
    lops
    -0.07
    rema
    -0.07
    loc
    -0.07
    POSITIVE LOGITS
    ethoven
    0.08
    atrix
    0.08
    autiful
    0.08
    aucoup
    0.08
    auty
    0.08
    cher
    0.08
    otime
    0.07
    arded
    0.07
     sure
    0.07
    auf
    0.07
    Activations Density 0.023%

    No Known Activations