© 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. 40392
    Prev
    Next
    INDEX
    Explanations

    references to the word "here."

    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
    yp
    -0.07
    ancy
    -0.07
    ĨĴ
    -0.07
    ses
    -0.06
    fall
    -0.06
    Ïħκ
    -0.06
    urb
    -0.06
    eln
    -0.06
    uce
    -0.06
    nt
    -0.05
    POSITIVE LOGITS
    edik
    0.07
    after
    0.07
    olid
    0.07
     Dock
    0.07
    alah
    0.07
    ket
    0.06
    zug
    0.06
    uhl
    0.06
    esting
    0.06
    ogi
    0.06
    Activations Density 0.017%

    No Known Activations