© 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. 78513
    Prev
    Next
    INDEX
    Explanations

    terms related to autism and associated behavioral issues

    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
    ZF
    -0.07
     Shock
    -0.06
    illon
    -0.06
    iler
    -0.06
     pul
    -0.06
    usan
    -0.06
     Branch
    -0.06
    astro
    -0.06
    tk
    -0.06
     Teil
    -0.06
    POSITIVE LOGITS
     behavior
    0.07
    elman
    0.07
    _behavior
    0.07
    anger
    0.07
     íĸīëıĻ
    0.07
    .DataBindings
    0.07
    arus
    0.06
     Medicaid
    0.06
     autistic
    0.06
    ervlet
    0.06
    Activations Density 0.019%

    No Known Activations