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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 16892
    Prev
    Next
    INDEX
    Explanations

    technical programming keywords and constructs

    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
    ucu
    -0.07
    asse
    -0.07
    ìĦľëĬĶ
    -0.07
     localVar
    -0.07
    .LookAndFeel
    -0.07
    Doctrine
    -0.07
    ãģ¡ãĤī
    -0.07
    iez
    -0.07
    awan
    -0.07
    house
    -0.06
    POSITIVE LOGITS
    s
    0.12
     Rahman
    0.07
    ../../../
    0.07
    IFO
    0.07
    krit
    0.07
    sar
    0.07
    said
    0.06
    sik
    0.06
    -speaking
    0.06
    न
    0.06
    Activations Density 0.001%

    No Known Activations