© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 15867
    Prev
    Next
    INDEX
    Explanations

    references to excerpts and quotations from other texts

    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
    ñana
    -0.06
    (Symbol
    -0.06
    ernen
    -0.06
    StateException
    -0.06
    hei
    -0.06
     Paren
    -0.06
     DONE
    -0.06
     McA
    -0.06
    커
    -0.06
    ifo
    -0.06
    POSITIVE LOGITS
     excerpt
    0.12
     extract
    0.12
     quote
    0.11
    excerpt
    0.11
    Quote
    0.10
     quoted
    0.10
     Extract
    0.10
    -quote
    0.10
    Extract
    0.09
     quotation
    0.09
    Activations Density 0.047%

    No Known Activations