© 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. 61619
    Prev
    Next
    INDEX
    Explanations

    terms related to fashion and clothing brands

    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
     Harness
    -0.06
     Nobel
    -0.06
    osit
    -0.06
    iment
    -0.06
     Enh
    -0.06
    port
    -0.06
     Belt
    -0.05
    ilig
    -0.05
    anca
    -0.05
     Titanic
    -0.05
    POSITIVE LOGITS
    ewan
    0.08
    åħĭæĸ¯
    0.07
     haus
    0.07
    ÄĽst
    0.07
    orners
    0.07
    efon
    0.07
    jeme
    0.07
    .Style
    0.07
    ocab
    0.07
    .cx
    0.07
    Activations Density 0.003%

    No Known Activations