© 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. 9-LLAMASCOPE-RES-131K
    11. 95272
    Prev
    Next
    INDEX
    Explanations

    references to governance and organizational structures

    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
    angkan
    -0.07
    fat
    -0.07
    abal
    -0.07
    yal
    -0.06
    OCKET
    -0.06
    ENCHMARK
    -0.06
    luvÃŃ
    -0.06
     Abed
    -0.06
    ýš
    -0.06
    partment
    -0.06
    POSITIVE LOGITS
    afort
    0.06
    usan
    0.06
     ware
    0.06
     Beam
    0.06
     BET
    0.06
    è¾Ľ
    0.06
     boz
    0.06
     Cong
    0.06
     skeleton
    0.06
     warp
    0.06
    Activations Density 0.014%

    No Known Activations