© 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. 96446
    Prev
    Next
    INDEX
    Explanations

    references to influential academic figures and their contributions

    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
    eson
    -0.07
    erre
    -0.07
    icom
    -0.06
    esp
    -0.06
    ifie
    -0.06
    igli
    -0.06
    oku
    -0.06
    cmd
    -0.06
    tier
    -0.06
    ros
    -0.06
    POSITIVE LOGITS
    äre
    0.07
    edia
    0.07
    verted
    0.07
     کاÙĦ
    0.07
    844
    0.06
    cesso
    0.06
    OLUMN
    0.06
     inverted
    0.06
    EDIA
    0.06
    /schema
    0.06
    Activations Density 0.001%

    No Known Activations