© 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. 18101
    Prev
    Next
    INDEX
    Explanations

    occurrences of specific numerical statistics or performance metrics in sports contexts

    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
    ATUS
    -0.09
    odos
    -0.08
    /umd
    -0.08
    arme
    -0.08
    xED
    -0.08
    象
    -0.07
    _utilities
    -0.07
    imu
    -0.07
    gie
    -0.07
    iders
    -0.07
    POSITIVE LOGITS
     Casino
    0.06
    .br
    0.06
     Hunt
    0.05
    itan
    0.05
     stiff
    0.05
    elin
    0.05
    uro
    0.05
    ļ
    0.05
    _PTR
    0.05
     Chapman
    0.05
    Activations Density 0.005%

    No Known Activations