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

    Neuronpedia

    APICircuit 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. 31-LLAMASCOPE-RES-131K
    6. 43461
    Prev
    Next
    INDEX
    Explanations

    HTML closing tags

    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
    leys
    -0.07
    #
    -0.06
     luder
    -0.06
    erring
    -0.06
    argent
    -0.06
    ÄĽj
    -0.06
    @nate
    -0.05
    ActionCreators
    -0.05
    2
    -0.05
    launcher
    -0.05
    POSITIVE LOGITS
    html
    0.19
     html
    0.15
    HTML
    0.13
    	html
    0.13
    htm
    0.13
    -html
    0.12
     HTML
    0.12
    (html
    0.12
    Html
    0.12
    _html
    0.11
    Activations Density 0.007%

    No Known Activations