© 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. 121348
    Prev
    Next
    INDEX
    Explanations

    references to educational institutions and their associated achievements

    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
    ëĿ½
    -0.08
    azzi
    -0.06
    upa
    -0.06
    åħ¬åľĴ
    -0.06
    èİ
    -0.06
    é£Ľ
    -0.06
    polator
    -0.06
    ÑħодиÑĤÑĮ
    -0.06
    #:
    -0.06
    sez
    -0.06
    POSITIVE LOGITS
     which
    0.10
    whose
    0.09
     whose
    0.09
    which
    0.08
     where
    0.07
     latter
    0.07
     (
    0.07
     ->
    0.07
    ï¼Įåħ¶ä¸Ń
    0.07
    (which
    0.07
    Activations Density 0.018%

    No Known Activations