© 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. 86541
    Prev
    Next
    INDEX
    Explanations

    code components and system functions related to data processing and management

    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
    cak
    -0.07
     Seznam
    -0.06
    tearDown
    -0.06
    preter
    -0.06
    Qualifier
    -0.06
    루
    -0.06
    Auf
    -0.06
    ubre
    -0.06
    лик
    -0.06
    ftware
    -0.06
    POSITIVE LOGITS
     нанеÑģ
    0.07
     пÑĢавда
    0.06
    yne
    0.06
    anko
    0.06
     Malone
    0.06
    Ïĥή
    0.06
    AMED
    0.06
    аÑĤÑĥ
    0.06
    zioni
    0.06
    _INCLUDED
    0.06
    Activations Density 0.020%

    No Known Activations