© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 86059
    Prev
    Next
    INDEX
    Explanations

    terms related to flavor and taste in food

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    elsen
    -0.09
    ew
    -0.09
     exp
    -0.07
    ucer
    -0.07
    nod
    -0.07
    ias
    -0.07
    دÙĬ
    -0.06
    urr
    -0.06
    oppel
    -0.06
    estre
    -0.06
    POSITIVE LOGITS
    ing
    0.08
    ruba
    0.07
    /color
    0.07
    blind
    0.07
    rant
    0.07
    408
    0.07
    оналÑĮ
    0.07
    ergus
    0.07
    )((((
    0.07
    less
    0.07
    Activations Density 0.007%

    No Known Activations