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. 43961
    Prev
    Next
    INDEX
    Explanations

    special characters or symbols

    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
    quin
    -0.06
    illac
    -0.06
    ONUS
    -0.06
    orsche
    -0.06
    ulen
    -0.06
     Laud
    -0.06
    unca
    -0.06
     Pearson
    -0.06
     ‘
    -0.06
    ofs
    -0.06
    POSITIVE LOGITS
     wrestlers
    0.15
     wrestling
    0.14
     Wrestling
    0.14
     wrestler
    0.14
     Wrest
    0.12
     BJ
    0.11
     Hardcore
    0.11
     promotions
    0.11
     Wrestle
    0.10
     hardcore
    0.10
    Activations Density 0.002%

    No Known Activations