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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 16482
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly question and exclamation marks

    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
    поÑĢ
    -0.08
    ooth
    -0.07
    etto
    -0.07
    fuse
    -0.07
    killer
    -0.07
    hir
    -0.07
    lando
    -0.07
    aceous
    -0.07
    fault
    -0.07
    roat
    -0.07
    POSITIVE LOGITS
    ï¸ı
    0.08
    [](
    0.07
    ¼åIJĪ
    0.06
    _construct
    0.06
    -style
    0.06
    ows
    0.06
    å¿Ĺ
    0.06
    inality
    0.06
    uration
    0.06
    pline
    0.06
    Activations Density 0.004%

    No Known Activations