© 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. 27322
    Prev
    Next
    INDEX
    Explanations

    events during a sports match

    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
    ắc
    -0.07
    ç¹ģ
    -0.07
    ripper
    -0.06
    ког
    -0.06
    anked
    -0.06
    ropol
    -0.06
     Rankings
    -0.06
    919
    -0.06
    оÑģÑĢед
    -0.06
    oric
    -0.06
    POSITIVE LOGITS
     traffic
    0.07
     pressure
    0.07
     Traffic
    0.07
    probe
    0.06
    urga
    0.06
     shots
    0.06
    оÑī
    0.06
    æĻ
    0.06
    ocu
    0.06
    cps
    0.06
    Activations Density 0.032%

    No Known Activations