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. 11479
    Prev
    Next
    INDEX
    Explanations

    specific character sequences or symbols indicative of language or special terms

    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
     utilizing
    -0.07
     utilization
    -0.06
     utilize
    -0.06
    Util
    -0.06
     utilized
    -0.06
     America
    -0.06
     america
    -0.06
     utilizes
    -0.06
     Util
    -0.05
    ÂĹ
    -0.05
    POSITIVE LOGITS
     EU
    0.14
     Brussels
    0.13
    EU
    0.12
    .eu
    0.12
     MEP
    0.12
     Member
    0.11
     municipalities
    0.11
     Europ
    0.10
     Europeans
    0.10
     Amsterdam
    0.10
    Activations Density 0.006%

    No Known Activations