© 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. 18539
    Prev
    Next
    INDEX
    Explanations

    code structures and programming elements related to logging and error handling

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    ayi
    -0.08
    кÑĥÑģ
    -0.07
     qua
    -0.06
    arcy
    -0.06
    ptom
    -0.06
    缼
    -0.06
    kola
    -0.06
    ÅĻet
    -0.06
    wen
    -0.06
    agus
    -0.06
    POSITIVE LOGITS
     MDB
    0.06
    ynchronously
    0.06
    ensen
    0.06
    âĢ¯
    0.06
    erek
    0.06
     nick
    0.06
    .defaults
    0.06
     ÐĶеÑĢжав
    0.05
    aku
    0.05
    anked
    0.05
    Activations Density 0.729%

    No Known Activations