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. 11522
    Prev
    Next
    INDEX
    Explanations

    references to research and academic topics

    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
    ’s
    -0.07
     Cas
    -0.06
    iker
    -0.06
     Jury
    -0.06
    ï¼ģï¼ģ↵↵
    -0.06
     tolerance
    -0.06
    ’↵
    -0.06
    ISCO
    -0.06
    isco
    -0.06
     Curl
    -0.06
    POSITIVE LOGITS
     '<
    0.09
     '
    0.09
     ('
    0.08
     <
    0.07
     '{@
    0.07
     <$
    0.07
    _customize
    0.07
    ,<
    0.07
     '[
    0.07
     âĹĦ
    0.07
    Activations Density 0.003%

    No Known Activations