© 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. 86437
    Prev
    Next
    INDEX
    Explanations

    variations of the word "hook" in different forms and contexts

    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
    amer
    -0.07
    iddet
    -0.07
    awks
    -0.07
    Ø´ÙĪد
    -0.06
    اÙħÙĩ
    -0.06
     hence
    -0.06
    pill
    -0.06
    ãģ£ãģ±ãģĦ
    -0.06
    ponce
    -0.06
    ikan
    -0.06
    POSITIVE LOGITS
    ing
    0.08
     Hook
    0.08
    jaw
    0.07
    ellar
    0.07
    tober
    0.07
    aroo
    0.07
    tight
    0.07
    er
    0.07
    ery
    0.07
    ered
    0.07
    Activations Density 0.006%

    No Known Activations