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. 44202
    Prev
    Next
    INDEX
    Explanations

    unique characters or elements from various languages 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
    avra
    -0.06
    agement
    -0.05
    æIJį
    -0.05
     hal
    -0.05
    orthy
    -0.05
     didSelectRowAtIndexPath
    -0.05
     bif
    -0.05
     tolua
    -0.05
    olesale
    -0.05
    loha
    -0.05
    POSITIVE LOGITS
     stamped
    0.12
     stamps
    0.12
     passport
    0.12
     immigration
    0.12
     stamp
    0.11
     Immigration
    0.11
     passports
    0.11
     visa
    0.11
     visas
    0.11
    visa
    0.11
    Activations Density 0.003%

    No Known Activations