© 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. 103853
    Prev
    Next
    INDEX
    Explanations

    comparisons of antibiotic treatment effectiveness in clinical trials

    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
    ÅĻen
    -0.08
    ŀĭ
    -0.07
    Ïģοι
    -0.06
     обÑĢа
    -0.06
    dge
    -0.06
    .Func
    -0.06
    860
    -0.06
    ÑĦÑĦ
    -0.06
    eliac
    -0.06
     typeid
    -0.06
    POSITIVE LOGITS
     versus
    0.08
     random
    0.08
     vs
    0.08
     treatment
    0.07
     Random
    0.07
    -Cs
    0.07
    stanov
    0.07
     Duration
    0.07
    -random
    0.07
     trial
    0.06
    Activations Density 0.053%

    No Known Activations