Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5382
    Prev
    Next
    INDEX
    Explanations

    references to the Greek god Dionysus and related themes

    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
    alled
    -0.08
    gett
    -0.07
    ulumi
    -0.07
    /cop
    -0.07
    leck
    -0.07
    çIJĨ
    -0.06
    compiler
    -0.06
    lify
    -0.06
    å°Ķ
    -0.06
    ัม
    -0.06
    POSITIVE LOGITS
    us
    0.07
    ys
    0.06
    iou
    0.06
    erk
    0.06
    åĽ
    0.06
    ysa
    0.06
     kolo
    0.06
    .GroupLayout
    0.06
    ç´ł
    0.06
    isas
    0.06
    Activations Density 0.004%

    No Known Activations