© 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. 17-LLAMASCOPE-RES-131K
    11. 83885
    Prev
    Next
    INDEX
    Explanations

    quantitative statistics related to sports performances

    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
    FileVersion
    -0.10
    .Version
    -0.09
    VERSION
    -0.09
     Version
    -0.08
    .version
    -0.08
     version
    -0.08
    _VERSION
    -0.07
     çīĪ
    -0.07
    _Version
    -0.07
     versions
    -0.07
    POSITIVE LOGITS
    undo
    0.07
    acy
    0.07
    kers
    0.06
    ushman
    0.06
    isy
    0.06
    chy
    0.06
    ãĥ¼ãĤ¹
    0.06
    URNS
    0.06
    å®
    0.06
    errick
    0.06
    Activations Density 0.074%

    No Known Activations