© 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. 91651
    Prev
    Next
    INDEX
    Explanations

    references to legal cases and medical negligence

    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
    AccessType
    -0.07
    Accessory
    -0.07
     milf
    -0.07
     copp
    -0.07
    agara
    -0.07
    rrha
    -0.06
    罪
    -0.06
    ABB
    -0.06
    awe
    -0.06
     Annunci
    -0.06
    POSITIVE LOGITS
     death
    0.07
     die
    0.07
    æŃ»
    0.07
     died
    0.07
    imas
    0.06
     star
    0.06
    ure
    0.06
    fold
    0.06
     chết
    0.06
     Facilities
    0.06
    Activations Density 0.010%

    No Known Activations