© 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. 38564
    Prev
    Next
    INDEX
    Explanations

    references to driving or operating vehicles and musical instruments

    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
    EDIA
    -0.07
    _UUID
    -0.07
    дав
    -0.07
    ossible
    -0.07
    OGLE
    -0.07
    ancellable
    -0.06
    SuccessListener
    -0.06
    zo
    -0.06
    erals
    -0.06
    iaux
    -0.06
    POSITIVE LOGITS
     camera
    0.06
     Cameras
    0.06
    à¤Ĺल
    0.06
     cameras
    0.06
     helm
    0.06
    onth
    0.06
    aset
    0.06
     unsub
    0.05
    ิà¸ķย
    0.05
    lif
    0.05
    Activations Density 0.005%

    No Known Activations