© 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. 108787
    Prev
    Next
    INDEX
    Explanations

    relationships between community cultural engagement and mental health outcomes

    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
    åĺĽ
    -0.06
     plage
    -0.06
     Zucker
    -0.06
    _ascii
    -0.06
     Ness
    -0.06
    ħn
    -0.06
    ento
    -0.06
    enou
    -0.06
     ìłľ
    -0.05
     Roose
    -0.05
    POSITIVE LOGITS
     outcome
    0.10
     outcomes
    0.09
    PropTypes
    0.07
     increased
    0.07
    outcome
    0.07
    chwitz
    0.07
     Outcome
    0.07
    abler
    0.07
     risk
    0.07
    pillar
    0.07
    Activations Density 0.023%

    No Known Activations