© 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. 93828
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate movement or action towards a goal

    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
     Hòa
    -0.07
    à¸Ĭร
    -0.07
    ünd
    -0.07
    Equip
    -0.07
    ικα
    -0.07
    WindowState
    -0.07
    .setViewport
    -0.06
     kvinde
    -0.06
    .liferay
    -0.06
    епÑĤи
    -0.06
    POSITIVE LOGITS
    VERRIDE
    0.07
     form
    0.07
     thereby
    0.07
     forming
    0.06
    ot
    0.06
    enny
    0.06
    vas
    0.06
     fit
    0.06
     ders
    0.05
    109
    0.05
    Activations Density 0.032%

    No Known Activations