© 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. 59189
    Prev
    Next
    INDEX
    Explanations

    the word "such" in various 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
    kn
    -0.07
    stalk
    -0.07
    ble
    -0.07
    hydr
    -0.07
    /renderer
    -0.06
    оÑĢг
    -0.06
    ROM
    -0.06
    rowable
    -0.06
    ville
    -0.06
    ABCDEFGHIJKLMNOP
    -0.06
    POSITIVE LOGITS
     kind
    0.10
    esser
    0.08
    -kind
    0.07
    errat
    0.07
    ylko
    0.07
    like
    0.07
    ichni
    0.07
    podob
    0.07
    ãģ®ãĤĪãģĨãģª
    0.06
    æł·çļĦ
    0.06
    Activations Density 0.015%

    No Known Activations