© 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. 121393
    Prev
    Next
    INDEX
    Explanations

    references to software functions and methods, particularly those related to handling events or data processing

    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
    oppable
    -0.07
    erk
    -0.07
    inan
    -0.06
    мена
    -0.06
    annot
    -0.06
    /*č↵
    -0.06
    cec
    -0.06
    oped
    -0.06
    nal
    -0.06
    places
    -0.06
    POSITIVE LOGITS
    347
    0.07
    YLES
    0.07
     INCIDENT
    0.07
    ouz
    0.07
    abyrin
    0.07
    acker
    0.06
    most
    0.06
    izzy
    0.06
    oner
    0.06
    uzzi
    0.06
    Activations Density 0.009%

    No Known Activations