© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1052
    Prev
    Next
    INDEX
    Explanations

    references to countries and complex variables in scientific contexts

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

    Technical terminology, variable names, and symbols that appear in programming code, mathematical formulas, or technical documentation.

    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
    UDO
    -0.07
    LAY
    -0.07
    vek
    -0.07
    pector
    -0.07
    FACT
    -0.07
    éĹ
    -0.06
    pekt
    -0.06
    Upper
    -0.06
    .spi
    -0.06
    èħIJ
    -0.06
    POSITIVE LOGITS
    ashion
    0.07
     Walsh
    0.06
    bor
    0.06
    Vien
    0.05
     fragment
    0.05
     Household
    0.05
    ash
    0.05
     Aires
    0.05
    LOPT
    0.05
    orie
    0.05
    Activations Density 0.213%

    No Known Activations