© 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. 38878
    Prev
    Next
    INDEX
    Explanations

    references to sports venues and stadiums

    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
    ahi
    -0.09
    bie
    -0.07
    bies
    -0.07
    acer
    -0.07
    OrDefault
    -0.07
    živ
    -0.07
    tings
    -0.07
    fully
    -0.07
    acom
    -0.06
    chers
    -0.06
    POSITIVE LOGITS
    -wide
    0.08
     grounds
    0.07
    lac
    0.07
    rats
    0.07
    iliar
    0.07
    TestMethod
    0.07
    stad
    0.07
    hya
    0.07
    KeyCode
    0.07
    lights
    0.07
    Activations Density 0.007%

    No Known Activations