© 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. 89575
    Prev
    Next
    INDEX
    Explanations

    phrases that highlight significant problems or challenges

    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
    Decoration
    -0.07
    aret
    -0.07
    оже
    -0.06
    aden
    -0.06
    olest
    -0.06
    esture
    -0.06
    ovel
    -0.06
    levision
    -0.06
    osen
    -0.06
    itten
    -0.06
    POSITIVE LOGITS
     increase
    0.07
    ekl
    0.06
     hell
    0.06
    ease
    0.06
     caÅĤ
    0.06
    TEGER
    0.06
    lette
    0.06
     delay
    0.06
    .twig
    0.06
    atrice
    0.06
    Activations Density 0.038%

    No Known Activations