© 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. 80709
    Prev
    Next
    INDEX
    Explanations

    descriptors related to types and characteristics of various entities and conditions

    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
    aje
    -0.06
    _LOOK
    -0.06
    emand
    -0.06
    im
    -0.06
    eland
    -0.06
    zes
    -0.05
     Kok
    -0.05
     Rak
    -0.05
    EventListener
    -0.05
     Kor
    -0.05
    POSITIVE LOGITS
     nature
    0.10
    nature
    0.09
    AINS
    0.07
     createContext
    0.07
    ãĥĭãĤ¢
    0.07
     tabi
    0.07
    iyel
    0.07
    .createTextNode
    0.07
    Ñĥди
    0.07
    çon
    0.07
    Activations Density 0.038%

    No Known Activations