© 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. 59968
    Prev
    Next
    INDEX
    Explanations

    HTML tags or markup elements

    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
    ↵↵
    -0.07
    ain
    -0.07
    iral
    -0.06
     authDomain
    -0.06
    ideographic
    -0.06
    igm
    -0.06
    annon
    -0.06
    464
    -0.06
    Ãły
    -0.06
     Gonz
    -0.06
    POSITIVE LOGITS
    edBy
    0.07
    edo
    0.07
    cest
    0.07
     drawn
    0.06
    atÃŃm
    0.06
    anta
    0.06
    eced
    0.06
     Berk
    0.06
    oner
    0.06
    aper
    0.06
    Activations Density 0.011%

    No Known Activations