© 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. 73835
    Prev
    Next
    INDEX
    Explanations

    issues related to video game performance and settings

    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
    -urlencoded
    -0.06
    ,
    -0.05
    å¤
    -0.05
     Jur
    -0.05
     Dy
    -0.05
    elay
    -0.05
     Ont
    -0.05
     Powers
    -0.05
    ective
    -0.05
     Greg
    -0.05
    POSITIVE LOGITS
    iband
    0.07
    аÑĤкÑĥ
    0.07
    benchmark
    0.07
    Benchmark
    0.07
    ARB
    0.07
    .Ptr
    0.07
    slaught
    0.07
    ãĥ³ãĥģ
    0.07
    .CLIENT
    0.07
     Chatt
    0.07
    Activations Density 0.006%

    No Known Activations