© 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. 81876
    Prev
    Next
    INDEX
    Explanations

    topics related to autism and its neurobiological factors

    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
     eldre
    -0.08
    ycastle
    -0.07
    -gnu
    -0.07
    ειο
    -0.07
     torino
    -0.07
    .dtd
    -0.07
    Ñĥда
    -0.06
    jmu
    -0.06
     Kund
    -0.06
    etrofit
    -0.06
    POSITIVE LOGITS
    asy
    0.06
     Bradley
    0.06
    ash
    0.06
    isy
    0.06
    nt
    0.06
    odd
    0.06
     deficits
    0.06
    hed
    0.06
     markers
    0.06
     in
    0.06
    Activations Density 0.036%

    No Known Activations