© 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. 40412
    Prev
    Next
    INDEX
    Explanations

    elements related to Android app development and layout attributes

    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
    ---</
    -0.07
    оÑģÑĢед
    -0.07
    lescope
    -0.07
    rimon
    -0.07
    (PR
    -0.06
    gii
    -0.06
    γη
    -0.06
    wald
    -0.06
    HWND
    -0.06
    ãĤ¤ãĤ¯
    -0.06
    POSITIVE LOGITS
    emann
    0.07
    ignKey
    0.07
    amina
    0.07
    amen
    0.06
    atori
    0.06
    ller
    0.06
     cách
    0.06
    ogi
    0.06
    keleton
    0.06
    .coordinate
    0.06
    Activations Density 0.001%

    No Known Activations