© 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. 71786
    Prev
    Next
    INDEX
    Explanations

    code comments or annotations

    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
    erton
    -0.08
    oux
    -0.07
    ais
    -0.07
    iger
    -0.06
    CFG
    -0.06
    alach
    -0.06
     Toll
    -0.06
    رÙĪض
    -0.06
    tron
    -0.06
    ages
    -0.06
    POSITIVE LOGITS
    uve
    0.07
    çIJĨ
    0.06
    mach
    0.06
    ãĥ«ãĤ¯
    0.06
     Ridley
    0.06
    endregion
    0.06
    ,...↵↵
    0.06
    tility
    0.06
    mam
    0.06
    INCLUDED
    0.06
    Activations Density 0.003%

    No Known Activations