© 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. 72529
    Prev
    Next
    INDEX
    Explanations

    numerical statistics related to competitive gaming performance

    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
    99
    -0.08
    953
    -0.06
    220
    -0.06
    801
    -0.06
    1
    -0.06
    569
    -0.06
    503
    -0.06
    252
    -0.06
    215
    -0.06
    gage
    -0.06
    POSITIVE LOGITS
    émon
    0.07
    ,'#
    0.07
    ismet
    0.07
    دار
    0.07
    irate
    0.07
    ancellable
    0.07
    uvo
    0.07
    iani
    0.07
    cak
    0.07
    Ý
    0.07
    Activations Density 0.053%

    No Known Activations