© 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. 73920
    Prev
    Next
    INDEX
    Explanations

    words associated with marvel and wonder 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
    pis
    -0.07
    ovan
    -0.07
    emean
    -0.06
    eless
    -0.06
    лаз
    -0.06
    pard
    -0.06
    .Selenium
    -0.06
    _charset
    -0.06
    .Orientation
    -0.05
    umble
    -0.05
    POSITIVE LOGITS
    ously
    0.09
    ing
    0.08
    ution
    0.07
    ulous
    0.07
    quiz
    0.07
    icious
    0.07
    licken
    0.07
    leich
    0.07
    sburg
    0.07
    ty
    0.07
    Activations Density 0.009%

    No Known Activations