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. 44346
    Prev
    Next
    INDEX
    Explanations

    special characters and diacritics in text

    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
     Stark
    -0.06
     Airways
    -0.06
     blackout
    -0.05
    ffc
    -0.05
    tt
    -0.05
     ‘
    -0.05
     Fly
    -0.05
    ckett
    -0.05
     Kidd
    -0.05
     BLACK
    -0.05
    POSITIVE LOGITS
     penis
    0.15
     Penis
    0.14
     shells
    0.12
     shell
    0.11
     worms
    0.11
     fossils
    0.10
     worm
    0.10
    shell
    0.10
     fossil
    0.10
    Shell
    0.10
    Activations Density 0.002%

    No Known Activations