© 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. 9-LLAMASCOPE-RES-131K
    11. 99203
    Prev
    Next
    INDEX
    Explanations

    terms related to chemical ingredients and safety

    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
    557
    -0.09
    erli
    -0.08
    ifton
    -0.08
    rowser
    -0.07
    lias
    -0.07
    ardown
    -0.07
    uliar
    -0.07
    lage
    -0.07
    arus
    -0.07
    emit
    -0.07
    POSITIVE LOGITS
    .bc
    0.06
    edback
    0.05
     Mouth
    0.05
     âĢı
    0.05
     Este
    0.05
    iel
    0.05
     batter
    0.05
    .normalize
    0.05
    athan
    0.05
     present
    0.05
    Activations Density 0.004%

    No Known Activations