© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 38574
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to content creation and posting

    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
    odem
    -0.07
    RICT
    -0.07
     Heard
    -0.06
    chio
    -0.06
    iko
    -0.06
    /Foundation
    -0.06
     Sands
    -0.06
    omik
    -0.06
    argin
    -0.06
    weight
    -0.06
    POSITIVE LOGITS
    =post
    0.07
    gresql
    0.06
    olle
    0.06
    postalcode
    0.06
    ures
    0.06
    uring
    0.06
     post
    0.06
    ulado
    0.06
    erior
    0.06
    greSQL
    0.06
    Activations Density 0.005%

    No Known Activations