© 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. 94280
    Prev
    Next
    INDEX
    Explanations

    past participles and forms of verbs related to creating, modifying, or managing items or processes

    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
    less
    -0.07
    ish
    -0.06
    stadt
    -0.06
    rame
    -0.06
     pros
    -0.06
    TP
    -0.06
     inc
    -0.05
    vise
    -0.05
     eng
    -0.05
    çļĦãģª
    -0.05
    POSITIVE LOGITS
    itung
    0.08
     xong
    0.08
    CCI
    0.08
    indhoven
    0.08
    ptron
    0.08
    oÄŁ
    0.08
    INFRINGEMENT
    0.08
    óż
    0.07
    ResultsController
    0.07
    á»ĩn
    0.07
    Activations Density 0.045%

    No Known Activations