© 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. 17-LLAMASCOPE-RES-131K
    11. 95947
    Prev
    Next
    INDEX
    Explanations

    terms related to the consumption of substances, particularly food and drinks

    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
    meer
    -0.09
    quier
    -0.07
    stro
    -0.07
    thur
    -0.07
    quo
    -0.07
    ìį¨
    -0.06
    angl
    -0.06
    们
    -0.06
    ("(%
    -0.06
    wan
    -0.06
    POSITIVE LOGITS
    /use
    0.08
    ancia
    0.08
     patterns
    0.07
    /storage
    0.07
    iParam
    0.07
    VisualStyle
    0.07
    ëŁī
    0.06
    éĩı
    0.06
    itures
    0.06
     Patterns
    0.06
    Activations Density 0.029%

    No Known Activations