© 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. 15-LLAMASCOPE-RES-131K
    11. 88292
    Prev
    Next
    INDEX
    Explanations

    negations in various contexts

    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
    ims
    -0.07
    -0.06
    inds
    -0.06
    oodles
    -0.06
    unction
    -0.06
    ulis
    -0.06
    .OnClickListener
    -0.06
    ies
    -0.06
    ernes
    -0.06
    ends
    -0.06
    POSITIVE LOGITS
    /stdc
    0.07
    à¹ĩà¸Ķ
    0.07
    ehir
    0.07
    ancode
    0.07
    .synthetic
    0.06
    erialize
    0.06
    //{{
    0.06
    BUTTONDOWN
    0.06
    ÑĢÑı
    0.06
    ¶Į
    0.06
    Activations Density 0.003%

    No Known Activations