© 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. 26856
    Prev
    Next
    INDEX
    Explanations

    various Java import statements and programming exceptions

    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
    berman
    -0.06
    mere
    -0.06
     NotImplementedError
    -0.06
     polož
    -0.06
    300
    -0.06
    ULO
    -0.06
    stro
    -0.06
    1
    -0.06
    '
    -0.06
     ať
    -0.05
    POSITIVE LOGITS
    asio
    0.07
    chandle
    0.07
    -wsj
    0.07
    _tF
    0.07
    ınıf
    0.07
    ROLL
    0.07
    RootElement
    0.07
    大åħ¨
    0.07
     YYS
    0.07
     [âĢ¦]↵↵
    0.07
    Activations Density 0.011%

    No Known Activations