© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 55513
    Prev
    Next
    INDEX
    Explanations

    references to partnerships and collaborations between organizations

    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
    ette
    -0.08
    erve
    -0.07
    Į¨
    -0.07
    aaaaaaaa
    -0.07
    .VERSION
    -0.07
    indir
    -0.07
    aring
    -0.07
    Ĩ
    -0.07
    รร
    -0.07
    ampoo
    -0.07
    POSITIVE LOGITS
     Äijá»ĥ
    0.09
    ë¡ľ
    0.07
     nhằm
    0.07
     for
    0.07
     whom
    0.07
     untuk
    0.07
     afin
    0.07
     to
    0.07
     mutually
    0.06
     длÑı
    0.06
    Activations Density 0.036%

    No Known Activations