© 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. 9-LLAMASCOPE-RES-131K
    11. 93987
    Prev
    Next
    INDEX
    Explanations

    references to annotations in programming or code-related contexts

    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
    opup
    -0.07
    minster
    -0.07
    Advisor
    -0.07
    olit
    -0.07
    hin
    -0.06
    _BOOT
    -0.06
     Ipsum
    -0.06
    iat
    -0.06
    oti
    -0.06
    ÑıÑģ
    -0.06
    POSITIVE LOGITS
    ERA
    0.07
    eer
    0.07
    orges
    0.06
    追
    0.06
    ево
    0.06
     Noon
    0.05
    .classes
    0.05
    multipart
    0.05
    饰
    0.05
    lando
    0.05
    Activations Density 0.010%

    No Known Activations