© 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. 39010
    Prev
    Next
    INDEX
    Explanations

    variations of the verb "take" in different 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
    iesel
    -0.08
    _KP
    -0.07
    utz
    -0.07
    \Bridge
    -0.07
    atte
    -0.07
    ربÙĩ
    -0.07
    vant
    -0.07
    wyn
    -0.07
    cesso
    -0.06
    urdy
    -0.06
    POSITIVE LOGITS
    ellen
    0.07
     duties
    0.07
    agram
    0.06
    stem
    0.06
     delivery
    0.06
    .fc
    0.06
    ÑĤÑĢон
    0.06
    SETS
    0.06
    gd
    0.05
    668
    0.05
    Activations Density 0.019%

    No Known Activations