© 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. 105029
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistical references

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

    Token fragments that often appear at grammatical junctions or the beginnings of proper nouns in news articles and technical documents.

    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
    eri
    -0.07
    meni
    -0.07
    	Copyright
    -0.07
    @(
    -0.06
    BuilderFactory
    -0.06
     dart
    -0.06
    apel
    -0.06
    æ´
    -0.06
     treff
    -0.06
    erosis
    -0.06
    POSITIVE LOGITS
     Aires
    0.07
    ODULE
    0.06
    udson
    0.06
    oyer
    0.06
     Posts
    0.06
    icense
    0.06
    UrlParser
    0.06
    vents
    0.06
    BackingField
    0.06
    sbin
    0.06
    Activations Density 0.002%

    No Known Activations