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. 43425
    Prev
    Next
    INDEX
    Explanations

    programming components and constructs in code

    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
    rido
    -0.07
    ucson
    -0.07
    SKTOP
    -0.07
    ackbar
    -0.07
    opr
    -0.06
    warf
    -0.06
    utzer
    -0.06
     qry
    -0.06
    ajo
    -0.06
    QueryParam
    -0.06
    POSITIVE LOGITS
     Markdown
    0.15
     markdown
    0.14
    Markdown
    0.14
    markdown
    0.13
     fenced
    0.12
    .md
    0.11
     pand
    0.11
     md
    0.11
     MD
    0.10
    (md
    0.10
    Activations Density 0.018%

    No Known Activations