© 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. 61531
    Prev
    Next
    INDEX
    Explanations

    words that suggest similarity or comparison among subjects

    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
    zew
    -0.07
    id
    -0.07
    ania
    -0.07
    ettes
    -0.07
    ette
    -0.06
    InChildren
    -0.06
    leftJoin
    -0.06
    ocalypse
    -0.06
     ↵↵
    -0.06
    VENT
    -0.06
    POSITIVE LOGITS
    adows
    0.07
    /of
    0.07
    abouts
    0.07
    iaux
    0.07
    thest
    0.07
    ÅĤÄħ
    0.07
     nhau
    0.07
    iating
    0.07
    /from
    0.07
     ÙħÛĮÙĦادÛĮ
    0.07
    Activations Density 0.089%

    No Known Activations