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. 5424
    Prev
    Next
    INDEX
    Explanations

    lists of scientific topics or concepts

    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
    ãĥ³ãĥī
    -0.08
    onio
    -0.08
    iaux
    -0.08
    engin
    -0.07
    nid
    -0.07
    ecies
    -0.07
    emez
    -0.07
    ScrollBar
    -0.07
    peats
    -0.07
    822
    -0.07
    POSITIVE LOGITS
    ask
    0.09
    Revision
    0.08
     Ask
    0.08
    /wiki
    0.08
     ask
    0.08
    ala
    0.08
    Ask
    0.07
     ÐĴики
    0.07
    ica
    0.07
    (thing
    0.07
    Activations Density 0.031%

    No Known Activations