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. 43788
    Prev
    Next
    INDEX
    Explanations

    contexts involving numerical comparisons or statistical data

    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
     CCP
    -0.08
     cocos
    -0.08
     BBB
    -0.07
    ImGui
    -0.07
     pandas
    -0.07
     GG
    -0.07
     gg
    -0.07
    çİĦ
    -0.07
     PPP
    -0.07
     MongoClient
    -0.07
    POSITIVE LOGITS
     Horn
    0.48
     horn
    0.40
    horn
    0.35
     horns
    0.34
     Hornets
    0.33
     Horm
    0.27
     Horny
    0.24
    ORN
    0.24
     horm
    0.24
    orn
    0.23
    Activations Density 0.007%

    No Known Activations