© 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. 75031
    Prev
    Next
    INDEX
    Explanations

    references to "Ward" and "wardrobe" indicating contexts related to caregiving and personal space

    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
    apolis
    -0.08
    ÏĤ
    -0.08
    ctors
    -0.07
    alted
    -0.07
    unci
    -0.07
    ittel
    -0.07
    curity
    -0.07
    ëħIJ
    -0.07
    ollen
    -0.07
    ordin
    -0.07
    POSITIVE LOGITS
    robe
    0.11
    ship
    0.07
    abouts
    0.06
    roots
    0.06
     bud
    0.06
    0.06
    uman
    0.06
    low
    0.06
    craft
    0.05
    ign
    0.05
    Activations Density 0.009%

    No Known Activations