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. 44327
    Prev
    Next
    INDEX
    Explanations

    mentions of audience reactions and appreciation in performance reviews

    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
    _COMPILE
    -0.08
    aign
    -0.07
    roduced
    -0.07
    aryawan
    -0.07
    ì§Ī
    -0.07
    iras
    -0.07
    tring
    -0.07
    peater
    -0.06
    traits
    -0.06
     sublic
    -0.06
    POSITIVE LOGITS
     loved
    0.16
     Loved
    0.14
     LO
    0.13
     liked
    0.12
     thoroughly
    0.12
     approved
    0.11
     r
    0.11
     commented
    0.11
     thought
    0.10
     really
    0.10
    Activations Density 0.037%

    No Known Activations