© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 97776
    Prev
    Next
    INDEX
    Explanations

    programming-related terminology

    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
    uria
    -0.07
    rado
    -0.06
    ä½į
    -0.06
    roje
    -0.06
    âķĹ
    -0.06
    ander
    -0.06
     Sutton
    -0.06
    oder
    -0.06
    /problems
    -0.06
    orses
    -0.06
    POSITIVE LOGITS
     Gors
    0.07
    दर
    0.07
    çĮ
    0.07
    ãĤ¹ãĥ¬
    0.07
     Jub
    0.07
    ivant
    0.06
    -regexp
    0.06
    ekl
    0.06
    (anchor
    0.06
    ãĤ»
    0.06
    Activations Density 0.001%

    No Known Activations