© 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. 86418
    Prev
    Next
    INDEX
    Explanations

    the word "why" and its variations, indicating a focus on questions or reasons

    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
    gne
    -0.07
    erde
    -0.06
    edback
    -0.06
    occo
    -0.06
    rale
    -0.06
    aki
    -0.06
    leh
    -0.06
    indle
    -0.06
    elden
    -0.06
    нак
    -0.06
    POSITIVE LOGITS
     Ø°ÙĦÙĥ
    0.07
     isso
    0.07
    дел
    0.06
    ause
    0.06
     milion
    0.06
    Ħ件
    0.06
    essa
    0.06
    ãģĿãĤĮãģ¯
    0.06
    ãģ¬
    0.06
    ainers
    0.06
    Activations Density 0.009%

    No Known Activations