© 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. 81664
    Prev
    Next
    INDEX
    Explanations

    instances of the word "covered" 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
    .Elements
    -0.08
    plaintext
    -0.07
    acon
    -0.07
    eniz
    -0.07
    adolu
    -0.07
    issen
    -0.07
    ิà¸ļ
    -0.07
    emmel
    -0.07
    uchi
    -0.07
    ì¶ľìŀ¥ìķĪë§Ī
    -0.06
    POSITIVE LOGITS
     covered
    0.09
     Covered
    0.08
     coverage
    0.08
    898
    0.07
     by
    0.07
    yl
    0.07
    894
    0.07
    -covered
    0.07
    coverage
    0.06
    covered
    0.06
    Activations Density 0.007%

    No Known Activations