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. 44305
    Prev
    Next
    INDEX
    Explanations

    special characters and symbols used in mathematical or scientific contexts

    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
    awe
    -0.06
    CDF
    -0.06
     Highway
    -0.06
     highway
    -0.06
     viá»ĩn
    -0.05
    .Authorization
    -0.05
     highways
    -0.05
    ©
    -0.05
    emy
    -0.05
     retreat
    -0.05
    POSITIVE LOGITS
     fixing
    0.16
    -fix
    0.16
     fix
    0.15
     Fix
    0.15
     betting
    0.14
    fix
    0.14
    Fix
    0.14
     FIXED
    0.14
     match
    0.14
     FIX
    0.14
    Activations Density 0.006%

    No Known Activations