© 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. 105500
    Prev
    Next
    INDEX
    Explanations

    the occurrences of the name "Cho."

    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
    ycop
    -0.08
    .scalablytyped
    -0.07
    ARING
    -0.07
    anzi
    -0.07
    allest
    -0.07
    égor
    -0.07
    adle
    -0.07
    ål
    -0.06
    egis
    -0.06
    -в
    -0.06
    POSITIVE LOGITS
    sterol
    0.08
     Hispan
    0.07
    lain
    0.07
    fulness
    0.06
    mie
    0.06
    croft
    0.06
    izo
    0.06
    rys
    0.06
    cie
    0.06
    over
    0.06
    Activations Density 0.012%

    No Known Activations