© 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. 14863
    Prev
    Next
    INDEX
    Explanations

    elements related to scoring and rules in competitive games

    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
    å·¡
    -0.06
    ç³
    -0.06
    umba
    -0.06
    .rand
    -0.06
    unte
    -0.06
     misc
    -0.06
    andom
    -0.06
    arness
    -0.05
     Ngh
    -0.05
    inem
    -0.05
    POSITIVE LOGITS
    ãĥ³ãĥģ
    0.08
    IGNAL
    0.07
     ties
    0.07
    ellido
    0.06
    (dot
    0.06
    Fix
    0.06
     Ø´Ùħ
    0.06
    ếp
    0.06
     tie
    0.06
    .CO
    0.06
    Activations Density 0.001%

    No Known Activations