© 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. 103584
    Prev
    Next
    INDEX
    Explanations

    various numerical values in scientific contexts

    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
    лаж
    -0.07
    ï½¢
    -0.07
    arness
    -0.06
    arer
    -0.06
    ersh
    -0.06
    วล
    -0.06
    Serialized
    -0.06
    zag
    -0.06
    /animations
    -0.06
    /filepath
    -0.06
    POSITIVE LOGITS
    vier
    0.07
    letic
    0.07
    rzy
    0.06
    egrator
    0.06
    lovak
    0.06
    unities
    0.06
    .Arguments
    0.06
    UMENT
    0.06
     Beverage
    0.06
    Downloader
    0.06
    Activations Density 0.001%

    No Known Activations