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. 44032
    Prev
    Next
    INDEX
    Explanations

    references to data models and attributes in programming 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
    idis
    -0.07
     roma
    -0.07
    .fromFunction
    -0.07
    arty
    -0.06
    .updateDynamic
    -0.06
    omu
    -0.06
    ndef
    -0.06
    ifton
    -0.06
    ewidth
    -0.06
     Slice
    -0.06
    POSITIVE LOGITS
    .xhtml
    0.09
    .html
    0.09
    .pdf
    0.09
    .gif
    0.09
    .jpeg
    0.08
    .png
    0.08
    .jpg
    0.08
    .text
    0.08
    .PNG
    0.08
    .mime
    0.08
    Activations Density 0.056%

    No Known Activations