© 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. 117947
    Prev
    Next
    INDEX
    Explanations

    terms related 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
    sterol
    -0.07
    /mol
    -0.07
    ainment
    -0.07
    emez
    -0.07
    uzzi
    -0.07
    reachable
    -0.07
    anvas
    -0.07
     BJ
    -0.07
    nist
    -0.07
    Touches
    -0.07
    POSITIVE LOGITS
     often
    0.07
     ace
    0.06
     Ace
    0.06
     sooner
    0.06
    Ñħо
    0.06
     tends
    0.06
     fix
    0.06
    zá
    0.06
     tend
    0.06
    ä¼ĺåĬ¿
    0.06
    Activations Density 0.007%

    No Known Activations