© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 740
    Prev
    Next
    INDEX
    Explanations

    expressions related to health and wellness tips, particularly focusing on beverages and their effects

    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
    opak
    -0.06
     squirrel
    -0.06
     bil
    -0.06
    ansson
    -0.06
    assis
    -0.06
    LBL
    -0.06
    berger
    -0.05
    wood
    -0.05
     plum
    -0.05
     Beats
    -0.05
    POSITIVE LOGITS
    doch
    0.06
    ูล
    0.06
    ejs
    0.06
    divid
    0.06
    ë£Į
    0.06
    /wiki
    0.06
    Utf
    0.06
     DISPATCH
    0.06
    dik
    0.06
    .MixedReality
    0.06
    Activations Density 0.010%

    No Known Activations