© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 38253
    Prev
    Next
    INDEX
    Explanations

    advice and strategies related to health and wellness

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    nt
    -0.09
    /or
    -0.07
    aka
    -0.07
    swire
    -0.06
    dt
    -0.06
    ÑĢд
    -0.06
    acades
    -0.06
     Sesso
    -0.06
    LLU
    -0.06
    yy
    -0.06
    POSITIVE LOGITS
    ëĬ¥
    0.07
     Heller
    0.07
    suming
    0.07
    _fsm
    0.07
    bsite
    0.07
    ród
    0.07
    stdClass
    0.06
    ORY
    0.06
    âĨIJ
    0.06
    olib
    0.06
    Activations Density 0.182%

    No Known Activations