© 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. 124219
    Prev
    Next
    INDEX
    Explanations

    references to governmental issues or legal texts related to health and safety

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Textual formatting elements that divide words, numbers, abbreviations, or create spacing between content sections.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    oj
    -0.08
     poil
    -0.08
    živ
    -0.08
    виÑĤ
    -0.08
    _________________↵↵
    -0.08
    ses
    -0.07
     rast
    -0.07
    !↵↵↵↵
    -0.07
    aģı
    -0.07
     tuto
    -0.07
    POSITIVE LOGITS
    §
    0.07
    avage
    0.07
    vůli
    0.06
    -Javadoc
    0.06
    .UTF
    0.06
    .MockMvc
    0.06
    -fontawesome
    0.06
    metro
    0.06
     sharedApplication
    0.06
    lash
    0.06
    Activations Density 1.000%

    No Known Activations