© 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. 18652
    Prev
    Next
    INDEX
    Explanations

    programming language constructs related to class and inheritance definitions

    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
    arn
    -0.06
    arian
    -0.06
    eel
    -0.06
    antan
    -0.06
    apan
    -0.06
     pat
    -0.06
     sv
    -0.06
    ismatic
    -0.06
    rost
    -0.05
    amber
    -0.05
    POSITIVE LOGITS
     NSObject
    0.10
    озем
    0.09
     StObject
    0.08
     BaseModel
    0.08
     QObject
    0.08
     RuntimeObject
    0.08
    BaseContext
    0.07
    NSObject
    0.07
    QObject
    0.07
    楽ãģĹ
    0.07
    Activations Density 0.015%

    No Known Activations