© 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. 61471
    Prev
    Next
    INDEX
    Explanations

    attributes related to dimensions and sizes in HTML and CSS

    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
    olean
    -0.07
    umer
    -0.07
    ottes
    -0.06
    antu
    -0.06
    aktu
    -0.06
    eyh
    -0.06
    wiÄħ
    -0.06
     Os
    -0.06
    usi
    -0.06
    ór
    -0.06
    POSITIVE LOGITS
     Dün
    0.06
    coma
    0.06
    Wunused
    0.06
    -toggler
    0.06
    æĻĵ
    0.06
    tee
    0.06
    teri
    0.06
    loser
    0.06
    æı¡
    0.06
    lycer
    0.06
    Activations Density 0.003%

    No Known Activations