© 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. 9-LLAMASCOPE-RES-131K
    11. 98216
    Prev
    Next
    INDEX
    Explanations

    properties and values in code, particularly related to CSS styles and layout

    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
    XP
    -0.07
    ancer
    -0.06
    heimer
    -0.06
    дем
    -0.06
    oute
    -0.06
    ach
    -0.06
    mts
    -0.06
    occo
    -0.06
    ikon
    -0.06
     Bea
    -0.06
    POSITIVE LOGITS
    uzu
    0.07
    emales
    0.06
    ATUS
    0.06
    ozÃŃ
    0.06
    rig
    0.06
    atus
    0.06
    gard
    0.06
     actionTypes
    0.06
    reck
    0.06
    SSERT
    0.06
    Activations Density 0.003%

    No Known Activations