© 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. 15-LLAMASCOPE-RES-131K
    11. 87532
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas and equations

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

    Mathematical formulas and equations in technical or scientific text, often describing relationships between variables or computational methods.

    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
    ardon
    -0.07
    ink
    -0.06
    vis
    -0.06
     Mart
    -0.06
    OCUS
    -0.06
    osen
    -0.06
    uli
    -0.06
    ç¥ĸ
    -0.06
     Sof
    -0.05
     jet
    -0.05
    POSITIVE LOGITS
     formula
    0.09
     relationships
    0.07
     Relationships
    0.07
    åħ¬å¼ı
    0.07
    Relationship
    0.07
    ahoma
    0.07
     relationship
    0.07
     Relationship
    0.07
     determination
    0.07
    readcr
    0.07
    Activations Density 0.043%

    No Known Activations