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. 22-LLAMASCOPE-RES-131K
    6. 5507
    Prev
    Next
    INDEX
    Explanations

    references to historical texts and scholars

    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
     yıldır
    -0.06
    ви
    -0.06
    raphics
    -0.06
    ç¹Ķ
    -0.06
     ìĽĢ
    -0.06
    á»ĩn
    -0.06
    Reviewed
    -0.06
     Artifact
    -0.06
    飾
    -0.06
    Buffer
    -0.05
    POSITIVE LOGITS
     writing
    0.12
     description
    0.12
     descriptions
    0.11
     wrote
    0.11
     mention
    0.11
     write
    0.10
     records
    0.10
     report
    0.10
     describe
    0.10
     writes
    0.10
    Activations Density 0.031%

    No Known Activations