© 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. 2036
    Prev
    Next
    INDEX
    Explanations

    the word "simply" in various contexts, indicating an emphasis on straightforwardness or ease

    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
    μÏĢο
    -0.07
    Ñĥже
    -0.07
    vd
    -0.07
    unj
    -0.07
    quartered
    -0.07
    ниÑģÑĤ
    -0.07
    .localized
    -0.06
    .eclipse
    -0.06
    ends
    -0.06
    igan
    -0.06
    POSITIVE LOGITS
    tons
    0.14
    -minded
    0.11
    ton
    0.09
    st
    0.09
    ifying
    0.09
    ifiable
    0.08
    mente
    0.08
    ifications
    0.08
    /plain
    0.08
    ified
    0.08
    Activations Density 0.011%

    No Known Activations