© 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. 9-LLAMASCOPE-RES-131K
    11. 96705
    Prev
    Next
    INDEX
    Explanations

    the prefix "un-" in various forms, 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
    istrovstvÃŃ
    -0.09
    	Copyright
    -0.07
    unter
    -0.07
    actively
    -0.07
    æĿ¿
    -0.07
    avn
    -0.07
    ownt
    -0.07
    opers
    -0.07
    Ñİ
    -0.07
    antine
    -0.07
    POSITIVE LOGITS
    idata
    0.07
    ude
    0.07
    idade
    0.07
    idos
    0.07
    tl
    0.07
    mam
    0.07
    nen
    0.06
    ĸī
    0.06
    nable
    0.06
    ERTICAL
    0.06
    Activations Density 0.056%

    No Known Activations