© 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 EvalsExportsAPI 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. 125730
    Prev
    Next
    INDEX
    Explanations

    references to mental health conditions, particularly related to ADHD and Autism

    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
    kp
    -0.07
    lander
    -0.06
    .echo
    -0.06
     Wand
    -0.06
    ozo
    -0.06
    ntl
    -0.06
    ục
    -0.06
     suspended
    -0.06
     Susp
    -0.06
    porn
    -0.06
    POSITIVE LOGITS
     Treat
    0.10
     treat
    0.08
     chemical
    0.08
     synd
    0.07
     dét
    0.07
     caused
    0.07
     treatments
    0.07
     science
    0.07
     disease
    0.07
     medical
    0.06
    Activations Density 0.009%

    No Known Activations