© 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. 89830
    Prev
    Next
    INDEX
    Explanations

    references to convictions and criminal charges

    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
    wald
    -0.08
    itz
    -0.07
    fü
    -0.07
    qi
    -0.07
    thon
    -0.07
    alle
    -0.07
    омеÑĤ
    -0.06
    affles
    -0.06
    frame
    -0.06
    ween
    -0.06
    POSITIVE LOGITS
     Conv
    0.07
    .conv
    0.07
     conv
    0.07
    assis
    0.07
    chor
    0.07
    .Conv
    0.07
    conv
    0.07
    (Conv
    0.07
     convictions
    0.07
    ambi
    0.07
    Activations Density 0.007%

    No Known Activations