© 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. 105232
    Prev
    Next
    INDEX
    Explanations

    phrases that describe data structures or UI components

    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
    awan
    -0.07
    Ỽp
    -0.07
    crm
    -0.07
    iddet
    -0.07
    icaret
    -0.07
    vang
    -0.07
    ["$
    -0.07
    lint
    -0.07
    arity
    -0.07
    issing
    -0.07
    POSITIVE LOGITS
     several
    0.09
     two
    0.09
     bunch
    0.07
    veral
    0.07
    两个
    0.07
     Several
    0.07
    æľīä¸Ģ
    0.06
     неÑģколÑĮкиÑħ
    0.06
     three
    0.06
     неÑģколÑĮ
    0.06
    Activations Density 0.016%

    No Known Activations