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. 44194
    Prev
    Next
    INDEX
    Explanations

    special characters and symbols, indicating a focus on non-standard text or formatting

    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
    isci
    -0.07
     Cincinnati
    -0.07
    ă
    -0.07
     Appalach
    -0.07
    æľŃ
    -0.07
     Appalachian
    -0.07
     Spokane
    -0.07
     Bangalore
    -0.07
     chicago
    -0.07
     Milwaukee
    -0.07
    POSITIVE LOGITS
     Caribbean
    0.14
     Jamaica
    0.10
     Trinidad
    0.10
     Bahamas
    0.10
     Island
    0.10
     island
    0.10
     Netherlands
    0.10
     hurricane
    0.10
     Irma
    0.09
     Dutch
    0.09
    Activations Density 0.004%

    No Known Activations