© 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. 73329
    Prev
    Next
    INDEX
    Explanations

    the Swedish word "och," which means "and."

    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
    ãĤ¸ãĤª
    -0.07
    ussen
    -0.07
    agar
    -0.07
    eselect
    -0.06
    inya
    -0.06
    ester
    -0.06
    atz
    -0.06
    Soap
    -0.06
    imm
    -0.06
    ieren
    -0.06
    POSITIVE LOGITS
     WARRANT
    0.08
     vice
    0.07
    ela
    0.07
    маÑħ
    0.06
    lém
    0.06
     GOODMAN
    0.06
    leta
    0.06
     density
    0.06
    .googleapis
    0.06
    alian
    0.06
    Activations Density 0.000%

    No Known Activations