© 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. 123310
    Prev
    Next
    INDEX
    Explanations

    mentions of personal development and career progression

    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
     Apprent
    -0.07
    ittance
    -0.07
    uyen
    -0.07
    áo
    -0.06
    tabpanel
    -0.06
    angu
    -0.06
    ätz
    -0.06
     huz
    -0.06
     Psychic
    -0.06
    okane
    -0.06
    POSITIVE LOGITS
     interest
    0.17
     interests
    0.17
     passion
    0.16
    interest
    0.14
     Interest
    0.14
     passions
    0.13
    Interest
    0.13
     interes
    0.13
     Passion
    0.12
     инÑĤеÑĢеÑģ
    0.12
    Activations Density 0.133%

    No Known Activations