© 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. 26888
    Prev
    Next
    INDEX
    Explanations

    instances of moral judgement and ethical considerations surrounding responsibility and consequences

    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
    izi
    -0.07
     Tits
    -0.07
    daÅŁ
    -0.07
    814
    -0.07
    lex
    -0.07
    629
    -0.07
    _IW
    -0.07
    ret
    -0.06
    istrovstvÃŃ
    -0.06
     OTHERWISE
    -0.06
    POSITIVE LOGITS
     consequences
    0.13
     consequence
    0.11
     repercussions
    0.09
     impact
    0.08
     loved
    0.07
     consequential
    0.07
     effects
    0.07
     Loved
    0.07
     impacts
    0.07
     implications
    0.07
    Activations Density 0.025%

    No Known Activations