© 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. 120183
    Prev
    Next
    INDEX
    Explanations

    the word "bull" and its variations, including phrases and contexts related to it

    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
    elay
    -0.07
    osy
    -0.07
    ements
    -0.07
    ogen
    -0.07
    ãģªãģĦ
    -0.07
    ement
    -0.07
    ettings
    -0.07
    å·ŀå¸Ĥ
    -0.07
    ialized
    -0.07
    ed
    -0.07
    POSITIVE LOGITS
    llll
    0.09
    sey
    0.08
    fighter
    0.08
    ustr
    0.08
    orca
    0.07
    Tube
    0.07
    ardin
    0.07
    fight
    0.07
    ied
    0.07
    frog
    0.07
    Activations Density 0.003%

    No Known Activations