© 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. 107275
    Prev
    Next
    INDEX
    Explanations

    evaluations of player performance in sports

    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
    plib
    -0.08
    .Butter
    -0.07
    ocracy
    -0.07
    (æ°´
    -0.07
    .UIManager
    -0.07
    овиÑĩ
    -0.07
    pread
    -0.07
     Kür
    -0.07
     NSCoder
    -0.07
     zda
    -0.07
    POSITIVE LOGITS
     linebacker
    0.08
     lineback
    0.07
     DL
    0.06
     search
    0.06
     force
    0.06
    -force
    0.06
    DL
    0.06
     active
    0.05
     Ful
    0.05
     Pir
    0.05
    Activations Density 0.129%

    No Known Activations