© 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. 96214
    Prev
    Next
    INDEX
    Explanations

    statements related to legal and political decisions

    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
     Neutral
    -0.08
    Neutral
    -0.07
    mî
    -0.07
     Nes
    -0.07
     neutral
    -0.07
    dock
    -0.07
    rompt
    -0.07
     Mezi
    -0.07
    ende
    -0.07
    alach
    -0.07
    POSITIVE LOGITS
     disappointing
    0.07
     decision
    0.07
     disappoint
    0.07
     tonight
    0.07
    decision
    0.06
     instead
    0.06
     Instead
    0.06
    brane
    0.06
     disappointment
    0.06
     decisions
    0.06
    Activations Density 0.015%

    No Known Activations