© 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. 9-LLAMASCOPE-RES-131K
    11. 95824
    Prev
    Next
    INDEX
    Explanations

    words indicating examples or instances of something

    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
    orda
    -0.07
    ved
    -0.07
    ugo
    -0.06
     ul
    -0.06
    him
    -0.06
    uls
    -0.06
    Advertisements
    -0.06
     Giz
    -0.06
     Recorder
    -0.06
    ³
    -0.06
    POSITIVE LOGITS
    дав
    0.07
    rame
    0.07
    ateg
    0.07
    plorer
    0.07
    .inline
    0.07
    awai
    0.06
    ligt
    0.06
    mars
    0.06
    avras
    0.06
    Äįky
    0.06
    Activations Density 0.015%

    No Known Activations