© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 104499
    Prev
    Next
    INDEX
    Explanations

    descriptions of game mechanics and interactions involving animated characters or 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
    icl
    -0.07
    perse
    -0.07
    nock
    -0.06
    unas
    -0.06
    ennie
    -0.06
    unn
    -0.06
    moid
    -0.06
    umm
    -0.06
    itesse
    -0.06
    aker
    -0.06
    POSITIVE LOGITS
    Mixin
    0.07
    ÂŃn
    0.06
     Trom
    0.06
    (DbContext
    0.06
    ÂŃt
    0.06
    icho
    0.06
    ELLOW
    0.06
    ington
    0.06
     ì¡°êµIJ
    0.06
    ars
    0.05
    Activations Density 0.010%

    No Known Activations