© 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. 42462
    Prev
    Next
    INDEX
    Explanations

    specific references and comparisons to items, places, or concepts

    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
    orda
    -0.08
    istrovstvÃŃ
    -0.08
    isÃŃ
    -0.07
    osh
    -0.07
    ìĿ´ëĿ¼ëĬĶ
    -0.07
    stan
    -0.06
    imir
    -0.06
    orem
    -0.06
    ulo
    -0.06
     meanwhile
    -0.06
    POSITIVE LOGITS
     ours
    0.10
     example
    0.09
     напÑĢимеÑĢ
    0.09
    ä¾ĭ
    0.09
     váºŃy
    0.08
     yours
    0.08
    998
    0.08
     ones
    0.08
    -example
    0.08
    example
    0.07
    Activations Density 0.028%

    No Known Activations