© 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. 63264
    Prev
    Next
    INDEX
    Explanations

    references to reputation and quality, particularly in business or artistic contexts

    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
    odable
    -0.07
    asca
    -0.07
    inia
    -0.07
     misd
    -0.07
    RAY
    -0.07
    isku
    -0.07
    ertas
    -0.06
    amina
    -0.06
    409
    -0.06
    erif
    -0.06
    POSITIVE LOGITS
     reputation
    0.29
     Reputation
    0.25
     reput
    0.24
    putation
    0.14
     fame
    0.13
     renown
    0.13
     Fame
    0.11
     reputed
    0.09
     notorious
    0.09
     ÑĢеп
    0.09
    Activations Density 0.111%

    No Known Activations