© 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. 14842
    Prev
    Next
    INDEX
    Explanations

    references to specific players and their performance in a sports context

    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
     publications
    -0.06
    iem
    -0.06
    ashes
    -0.06
    ãĥĥãĥĦ
    -0.06
    mes
    -0.06
     viz
    -0.06
     xếp
    -0.06
     Exc
    -0.06
    ãĤŃãĥ³ãĤ°
    -0.06
     publication
    -0.06
    POSITIVE LOGITS
     McCart
    0.08
    emoc
    0.08
     célib
    0.06
    責
    0.06
    oner
    0.06
    óst
    0.06
    tainment
    0.06
     Appearance
    0.06
    dio
    0.06
    -native
    0.06
    Activations Density 0.011%

    No Known Activations