© 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 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. 9-LLAMASCOPE-RES-131K
    11. 96709
    Prev
    Next
    INDEX
    Explanations

    references to specific years and events in sports history

    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
    ovich
    -0.06
    chef
    -0.05
    ãĢħ
    -0.05
    thes
    -0.05
     technique
    -0.05
    à¤Łà¤¨
    -0.05
    ови
    -0.05
     ä½IJ
    -0.05
    çµĦ
    -0.05
    zip
    -0.05
    POSITIVE LOGITS
    arness
    0.08
    kich
    0.07
    apur
    0.07
    SetName
    0.07
     misd
    0.07
    idunt
    0.07
    kick
    0.06
    Kick
    0.06
    qli
    0.06
    rowning
    0.06
    Activations Density 0.020%

    No Known Activations