© 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. 15-LLAMASCOPE-RES-131K
    11. 86159
    Prev
    Next
    INDEX
    Explanations

    references to safety and responsible driving practices

    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
    kick
    -0.06
    Handle
    -0.06
     actionTypes
    -0.06
    æĸŃ
    -0.06
     handled
    -0.05
    ifetime
    -0.05
    æŁĦ
    -0.05
    elay
    -0.05
     se
    -0.05
    _handle
    -0.05
    POSITIVE LOGITS
     Speed
    0.10
    Speed
    0.10
    _Speed
    0.09
     speed
    0.09
    -speed
    0.09
    .Speed
    0.09
    speed
    0.08
     SPEED
    0.08
    .speed
    0.08
    _speed
    0.08
    Activations Density 0.003%

    No Known Activations