© 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. 1186
    Prev
    Next
    INDEX
    Explanations

    phrases indicating advice or suggestions regarding policy changes

    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
    isko
    -0.06
    .spatial
    -0.06
    otor
    -0.06
    rite
    -0.06
    Descending
    -0.06
    åº
    -0.06
    von
    -0.06
    orman
    -0.06
    ownt
    -0.06
    regon
    -0.06
    POSITIVE LOGITS
     impending
    0.08
     progress
    0.07
    ORTH
    0.07
    udu
    0.07
    deme
    0.07
     changes
    0.06
    itom
    0.06
     dangers
    0.06
     plans
    0.06
     how
    0.06
    Activations Density 0.014%

    No Known Activations