© 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. 30424
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "when"

    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
    krv
    -0.10
    SizeMode
    -0.09
    ucs
    -0.08
    luž
    -0.08
    anela
    -0.08
    Ñİк
    -0.08
    ussen
    -0.08
    ansk
    -0.08
    ãģĹãĤĩãģĨ
    -0.08
    unately
    -0.08
    POSITIVE LOGITS
    soever
    0.14
    /if
    0.14
     we
    0.11
     they
    0.11
    -нибÑĥдÑĮ
    0.11
     it
    0.11
    -либо
    0.10
     you
    0.10
    EVER
    0.10
    abouts
    0.10
    Activations Density 0.108%

    No Known Activations