© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 73447
    Prev
    Next
    INDEX
    Explanations

    acknowledgments and expressions of gratitude 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
    baugh
    -0.08
    eru
    -0.08
    :↵↵↵↵↵↵
    -0.07
    ysi
    -0.07
    isine
    -0.07
     ún
    -0.07
    894
    -0.07
    èĹį
    -0.06
    å¸ĸ
    -0.06
    baum
    -0.06
    POSITIVE LOGITS
    ืà¸Ńà¸Ķ
    0.06
    aging
    0.06
     referee
    0.06
     convin
    0.05
    roid
    0.05
    olders
    0.05
     elementType
    0.05
     cour
    0.05
     swinger
    0.05
    gewater
    0.05
    Activations Density 0.031%

    No Known Activations