© 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. 55133
    Prev
    Next
    INDEX
    Explanations

    references to autism and related conditions

    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
    udad
    -0.07
    inery
    -0.07
    dech
    -0.07
     AVL
    -0.07
    @student
    -0.07
    fak
    -0.06
    fcn
    -0.06
     Fu
    -0.06
    iefs
    -0.06
    ãĤ¤ãĤº
    -0.06
    POSITIVE LOGITS
     autism
    0.11
     Autism
    0.10
     autistic
    0.10
     communication
    0.08
     spectrum
    0.08
     stim
    0.08
     Spectrum
    0.08
    communication
    0.08
     disorder
    0.08
     ASD
    0.07
    Activations Density 0.064%

    No Known Activations