© 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. 96216
    Prev
    Next
    INDEX
    Explanations

    expressions of mental health struggles and personal experiences related to anxiety and ADHD

    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
    oga
    -0.07
    iken
    -0.07
    wap
    -0.06
     Tro
    -0.06
    elsif
    -0.06
    HEME
    -0.06
    ละ
    -0.06
     headaches
    -0.06
    spell
    -0.06
    ейн
    -0.06
    POSITIVE LOGITS
    icut
    0.07
     untreated
    0.07
     medication
    0.07
    à¸Ħวà¸ļà¸Ħ
    0.07
    amient
    0.07
     treatment
    0.06
     Trigger
    0.06
     chatte
    0.06
     triggers
    0.06
     mang
    0.06
    Activations Density 0.016%

    No Known Activations