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. 44182
    Prev
    Next
    INDEX
    Explanations

    characters and symbols, particularly those related to textual formatting or code

    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
     Hyundai
    -0.06
    .MixedReality
    -0.06
     tük
    -0.06
     Huawei
    -0.06
     autoplay
    -0.06
    afs
    -0.06
     Analyst
    -0.06
    oplayer
    -0.06
    xec
    -0.06
    à¸Ĭาà¸ķ
    -0.06
    POSITIVE LOGITS
     bike
    0.20
     Bike
    0.20
     bicycle
    0.19
     cycling
    0.18
     biking
    0.18
     cyclists
    0.18
     Bicycle
    0.18
     bicy
    0.18
     bikes
    0.17
     cyclist
    0.17
    Activations Density 0.002%

    No Known Activations