© 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. 40011
    Prev
    Next
    INDEX
    Explanations

    questions and assertions regarding identity and legality

    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
     Heights
    -0.07
    erland
    -0.07
    γα
    -0.07
    terdam
    -0.07
     ÑģлÑĥÑĩай
    -0.06
    mam
    -0.06
    illin
    -0.06
    inan
    -0.06
    orra
    -0.06
    maid
    -0.06
    POSITIVE LOGITS
    /how
    0.08
     so
    0.08
    nt
    0.07
     we
    0.07
     suddenly
    0.07
     everyone
    0.06
    esis
    0.06
    atter
    0.06
    è¿Ļä¹Ī
    0.06
     important
    0.06
    Activations Density 0.007%

    No Known Activations