© 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. 17-LLAMASCOPE-RES-131K
    11. 95520
    Prev
    Next
    INDEX
    Explanations

    U.S. state abbreviations and associated locations

    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
    reff
    -0.07
    athi
    -0.07
    elts
    -0.06
    ctype
    -0.06
    acements
    -0.06
     actionTypes
    -0.06
    ipel
    -0.06
    whelming
    -0.06
     remarks
    -0.06
    ayar
    -0.06
    POSITIVE LOGITS
    /TT
    0.08
    agram
    0.07
     Affero
    0.07
    è¦ĭ
    0.07
     Ú©ÛĮÙģ
    0.07
    cul
    0.07
    /request
    0.06
    Sampler
    0.06
    ál
    0.06
    ZN
    0.06
    Activations Density 0.014%

    No Known Activations