© 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. 128900
    Prev
    Next
    INDEX
    Explanations

    directional phrases and descriptions of visibility in a landscape

    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
    .net
    -0.07
     nom
    -0.06
    inal
    -0.06
    core
    -0.06
    iders
    -0.06
     Advoc
    -0.06
    oload
    -0.06
    .blog
    -0.06
     service
    -0.06
     dün
    -0.06
    POSITIVE LOGITS
    AGO
    0.07
    iggins
    0.07
    viewer
    0.07
    ehler
    0.07
     artifact
    0.07
    .EventQueue
    0.07
    ago
    0.07
    cene
    0.07
    iyon
    0.07
     rooft
    0.07
    Activations Density 0.008%

    No Known Activations