© 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. 38228
    Prev
    Next
    INDEX
    Explanations

    expressions of courage and the willingness to confront challenges

    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
    ewire
    -0.07
    quip
    -0.07
    orges
    -0.07
    kup
    -0.06
    avoid
    -0.06
    aldi
    -0.06
    gid
    -0.06
    agle
    -0.06
    ibox
    -0.06
    enal
    -0.06
    POSITIVE LOGITS
     risk
    0.12
     Risk
    0.10
     bold
    0.09
    risk
    0.09
     daring
    0.09
     risks
    0.09
    Risk
    0.09
    bold
    0.09
     unpopular
    0.09
     challenge
    0.09
    Activations Density 0.053%

    No Known Activations