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. 11473
    Prev
    Next
    INDEX
    Explanations

    specific mathematical symbols and notations

    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
     football
    -0.07
     ì¶ķ구
    -0.06
    ozilla
    -0.06
    FAIL
    -0.06
    Dispatch
    -0.06
     rugby
    -0.06
    té
    -0.06
    iage
    -0.06
     Laud
    -0.06
    football
    -0.06
    POSITIVE LOGITS
     Pool
    0.16
     pool
    0.16
    Pool
    0.14
    POOL
    0.13
    pool
    0.13
     pools
    0.12
    (pool
    0.12
     cue
    0.11
     pooling
    0.11
    .Pool
    0.11
    Activations Density 0.006%

    No Known Activations