© 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. 117369
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "when" 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
    à¹Ĥย
    -0.07
    lust
    -0.07
    ixo
    -0.07
    istrovstvÃŃ
    -0.07
    coder
    -0.07
    aus
    -0.07
    imeo
    -0.07
    kest
    -0.06
    ÑĮ
    -0.06
    sted
    -0.06
    POSITIVE LOGITS
     need
    0.07
    rescia
    0.06
     your
    0.06
     Combined
    0.06
    822
    0.06
     lou
    0.06
    aket
    0.06
     needed
    0.06
     Lou
    0.06
     you
    0.06
    Activations Density 0.011%

    No Known Activations