© 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 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. 59518
    Prev
    Next
    INDEX
    Explanations

    occurrences of the prefix 'un' and its variations, indicating negation or reversal

    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
    /***/
    -0.07
    .hwp
    -0.07
    Òij
    -0.07
     QUI
    -0.07
    گرÛĮ
    -0.07
    stdafx
    -0.07
    åº
    -0.06
    ãĥ«ãĤ¯
    -0.06
    ожеÑĤ
    -0.06
     -----------------------------------------------------------------------------↵
    -0.06
    POSITIVE LOGITS
    alsy
    0.06
    êm
    0.06
    sville
    0.06
    prech
    0.06
    isi
    0.06
    iere
    0.06
    mers
    0.06
     possibility
    0.06
    pr
    0.06
    bole
    0.06
    Activations Density 0.020%

    No Known Activations