© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 92112
    Prev
    Next
    INDEX
    Explanations

    statistics and information related to mental health issues, specifically focusing on anxiety and depression among men

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    TypeInfo
    -0.07
     phóng
    -0.07
     Hatch
    -0.07
    æ·
    -0.07
     onCreateView
    -0.06
    FINITY
    -0.06
    StringEncoding
    -0.06
    UBLE
    -0.06
    agua
    -0.06
    ç©´
    -0.06
    POSITIVE LOGITS
     mental
    0.14
     Mental
    0.14
     depression
    0.13
    mental
    0.12
     suicide
    0.11
     Suicide
    0.10
     Depression
    0.10
     stress
    0.09
     antidepress
    0.09
    ental
    0.08
    Activations Density 0.214%

    No Known Activations