© 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. 69591
    Prev
    Next
    INDEX
    Explanations

    instances of the word "while" 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
    teenth
    -0.07
    etc
    -0.06
    rist
    -0.06
    ied
    -0.06
    ahi
    -0.06
    lean
    -0.06
    chang
    -0.06
    um
    -0.06
    _np
    -0.06
    onto
    -0.06
    POSITIVE LOGITS
    s
    0.08
    tul
    0.08
    igen
    0.07
    ska
    0.06
    hud
    0.06
    romosome
    0.06
    sÃŃ
    0.06
    egers
    0.06
    indre
    0.06
    enschaft
    0.06
    Activations Density 0.014%

    No Known Activations