© 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. 69671
    Prev
    Next
    INDEX
    Explanations

    mathematical or graph-theoretical notation and properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Mathematical notation representing partitions, sets, and functions in scientific/technical papers, particularly in graph theory where notations like mathcal{P}, mathcal{G}, equipartitions, and probability expressions appear in formula contexts.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    ,and
    -0.06
     ...,
    -0.06
     swear
    -0.06
    ,but
    -0.05
     nasty
    -0.05
     leftover
    -0.05
     /*!↵
    -0.05
     a
    -0.05
     trib
    -0.05
    fabs
    -0.05
    POSITIVE LOGITS
    vvm
    0.09
     právÄĽ
    0.09
    ëį
    0.09
    ÑģÑĮого
    0.09
    aleb
    0.09
     [âĢ¦]↵↵
    0.09
    INCLUDED
    0.09
    abay
    0.09
    kelas
    0.08
    hora
    0.08
    Activations Density 10.292%

    No Known Activations