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. 22-LLAMASCOPE-RES-131K
    6. 5619
    Prev
    Next
    INDEX
    Explanations

    historical dates and references to chronological events

    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
    haf
    -0.07
    æ£ĭçīĮ
    -0.06
    .SingleOrDefault
    -0.06
    olin
    -0.06
    .contract
    -0.06
     Stap
    -0.06
    plib
    -0.06
    alion
    -0.06
    ollo
    -0.06
    यर
    -0.06
    POSITIVE LOGITS
     Pearson
    0.07
    ëħĦ
    0.06
    alth
    0.06
    erc
    0.06
    icone
    0.06
    hol
    0.06
     memor
    0.06
     Pills
    0.06
    ãĤ§
    0.06
    196
    0.06
    Activations Density 0.006%

    No Known Activations