© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 125194
    Prev
    Next
    INDEX
    Explanations

    locations or spaces referenced in the text

    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
    lords
    -0.07
    анÑģи
    -0.07
     addCriterion
    -0.07
    arten
    -0.07
    zell
    -0.06
    оналÑĮ
    -0.06
    haf
    -0.06
    HEMA
    -0.06
    otta
    -0.06
    eldon
    -0.06
    POSITIVE LOGITS
     area
    0.08
    Ģìŀ¥
    0.07
     Area
    0.06
     located
    0.06
    à¸ģลาà¸ĩ
    0.06
    parator
    0.06
    builtin
    0.06
    lik
    0.05
    uman
    0.05
     where
    0.05
    Activations Density 0.037%

    No Known Activations