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. 87421
    Prev
    Next
    INDEX
    Explanations

    references to products, models, or brands related to health and fitness technology

    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
    hang
    -0.09
    allet
    -0.08
    ins
    -0.07
    ument
    -0.07
    illin
    -0.07
    asl
    -0.07
    all
    -0.07
    ouch
    -0.07
    weg
    -0.07
    h
    -0.07
    POSITIVE LOGITS
    atan
    0.08
    ecut
    0.08
    ur
    0.07
    ylie
    0.07
    anus
    0.07
    è
    0.07
    inding
    0.07
    rix
    0.07
    ands
    0.07
    roc
    0.07
    Activations Density 0.109%

    No Known Activations