© 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. 5-LLAMASCOPE-RES-131K
    11. 125716
    Prev
    Next
    INDEX
    Explanations

    specific references to books, authors, and bibliographic details

    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
    hab
    -0.07
     Hab
    -0.06
     hab
    -0.06
    ãĥĶãĥ¼
    -0.06
    å¡ŀ
    -0.06
     bana
    -0.06
    YO
    -0.06
    æ¡Ĥ
    -0.06
    ãģ»ãģĨ
    -0.06
    åĺĽ
    -0.06
    POSITIVE LOGITS
    iek
    0.06
    ıc
    0.06
    elyn
    0.06
    rouch
    0.06
    ague
    0.06
     Caucus
    0.06
    ih
    0.06
    esch
    0.06
    'gc
    0.06
    iesen
    0.06
    Activations Density 0.011%

    No Known Activations