© 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. 70744
    Prev
    Next
    INDEX
    Explanations

    references to stock images and their sources

    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
    rish
    -0.07
    ripp
    -0.07
     Bened
    -0.07
    rek
    -0.07
    abbr
    -0.06
    quo
    -0.06
     Ping
    -0.06
    umni
    -0.06
    cer
    -0.06
    aggio
    -0.06
    POSITIVE LOGITS
    AAA
    0.07
    .require
    0.07
    ewis
    0.06
    endra
    0.06
    Borders
    0.06
    epam
    0.06
    indsight
    0.06
    zych
    0.06
     ÙĤدر
    0.06
     bey
    0.06
    Activations Density 0.004%

    No Known Activations