© 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. 93308
    Prev
    Next
    INDEX
    Explanations

    the name "Gardner" and its variations, indicating a focus on gardening or individuals with that name

    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
    omid
    -0.08
    ryo
    -0.08
    ipzig
    -0.07
    üst
    -0.07
    cgi
    -0.07
    stances
    -0.07
    xdb
    -0.07
    stance
    -0.07
    ieurs
    -0.07
    .gdx
    -0.07
    POSITIVE LOGITS
    tur
    0.06
     Honest
    0.06
    tak
    0.06
    ajo
    0.06
     Sick
    0.06
    ner
    0.06
     bud
    0.05
     Feld
    0.05
    ç´į
    0.05
    Äħż
    0.05
    Activations Density 0.010%

    No Known Activations