© 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. 108802
    Prev
    Next
    INDEX
    Explanations

    expressions of grief and emotional distress

    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
    rada
    -0.08
    ysi
    -0.07
    ROL
    -0.07
    ÙħÙĨ
    -0.07
    सर
    -0.07
    rika
    -0.07
    POSE
    -0.07
    rita
    -0.07
    /generated
    -0.07
    afd
    -0.07
    POSITIVE LOGITS
     worry
    0.07
     concern
    0.07
     reunion
    0.07
     reun
    0.07
     search
    0.06
     fret
    0.06
    łģ
    0.06
     worried
    0.06
    pie
    0.06
     pie
    0.06
    Activations Density 0.046%

    No Known Activations