© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 69019
    Prev
    Next
    INDEX
    Explanations

    references to rejection and encouragement in creative pursuits

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    anders
    -0.07
    acht
    -0.06
    rought
    -0.06
     trag
    -0.06
    ZR
    -0.06
    758
    -0.05
     pledges
    -0.05
    SWG
    -0.05
     capt
    -0.05
     pre
    -0.05
    POSITIVE LOGITS
     rejection
    0.12
     rejected
    0.09
     reject
    0.08
    rejected
    0.07
    .scalablytyped
    0.07
     rejects
    0.07
     Thick
    0.07
    rej
    0.07
     Reject
    0.07
     Failed
    0.07
    Activations Density 0.015%

    No Known Activations