© 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. 17-LLAMASCOPE-RES-131K
    11. 29397
    Prev
    Next
    INDEX
    Explanations

    references to assessments, support, and employment-related scenarios

    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
    ingu
    -0.06
    ao
    -0.06
     mi
    -0.05
     Blond
    -0.05
     al
    -0.05
    ed
    -0.05
     Mi
    -0.05
    strand
    -0.05
     Starting
    -0.05
    [
    -0.05
    POSITIVE LOGITS
    #
    0.09
     VÅ¡ech
    0.08
     takson
    0.08
     nuest
    0.08
     Redistributions
    0.08
    /Foundation
    0.08
     ******************************************************************************↵
    0.08
    adaÅŁ
    0.08
    AEA
    0.08
    cept
    0.07
    Activations Density 0.019%

    No Known Activations