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

    Neuronpedia

    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. 130132
    Prev
    Next
    INDEX
    Explanations

    occurrences of the verb "got" and its variations

    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
     harms
    -0.07
     пÑĢиÑĤ
    -0.07
    ouncements
    -0.07
    ấu
    -0.07
    ignKey
    -0.07
    nees
    -0.07
    epad
    -0.07
    ноÑģÑı
    -0.06
    pery
    -0.06
    :CGRect
    -0.06
    POSITIVE LOGITS
    arkin
    0.07
    outers
    0.06
     introduced
    0.06
     Dw
    0.06
    elite
    0.06
    juan
    0.06
    crest
    0.06
     Garrison
    0.06
     Introduced
    0.06
    hani
    0.06
    Activations Density 0.025%

    No Known Activations