© 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. 53865
    Prev
    Next
    INDEX
    Explanations

    statements regarding the effects and regulations of medications and treatments

    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
    jÃŃm
    -0.07
    ylon
    -0.07
     bás
    -0.07
    _RADIO
    -0.07
    ома
    -0.07
    onso
    -0.07
    VERAGE
    -0.07
    mma
    -0.07
    ãĥĥãĤ¯
    -0.06
    gcd
    -0.06
    POSITIVE LOGITS
     checker
    0.07
     رس
    0.06
     dos
    0.06
     comb
    0.06
     con
    0.06
    addon
    0.06
     drug
    0.06
     ca
    0.06
     d
    0.06
    435
    0.06
    Activations Density 0.022%

    No Known Activations