© 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. 123336
    Prev
    Next
    INDEX
    Explanations

    emotions and states of well-being

    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
    ylon
    -0.09
     Darkness
    -0.07
    erness
    -0.07
    iswa
    -0.06
    stalk
    -0.06
    ERTICAL
    -0.06
    expression
    -0.06
    ãĤ¹ãĥ¬
    -0.06
    tone
    -0.06
     Carp
    -0.06
    POSITIVE LOGITS
     conscience
    0.17
     guilt
    0.12
     feel
    0.10
     Feel
    0.10
    Feel
    0.09
     feels
    0.09
     knowing
    0.08
     worry
    0.08
     feeling
    0.08
    feel
    0.08
    Activations Density 0.038%

    No Known Activations