© 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. 121641
    Prev
    Next
    INDEX
    Explanations

    code-related syntax and tokens in programming

    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
    yn
    -0.07
    ARGIN
    -0.07
    讯
    -0.06
     Zus
    -0.06
    %D
    -0.06
    ged
    -0.06
    ney
    -0.06
    LOUD
    -0.06
    951
    -0.06
    149
    -0.06
    POSITIVE LOGITS
    izr
    0.08
    apel
    0.07
    outil
    0.07
     Zag
    0.07
    atel
    0.07
    anders
    0.06
    GameManager
    0.06
    eor
    0.06
    apers
    0.06
     Sovere
    0.06
    Activations Density 0.025%

    No Known Activations