© 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. 117884
    Prev
    Next
    INDEX
    Explanations

    phrases related to the experience and duration of life events

    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
    mw
    -0.07
    Locator
    -0.07
    iminal
    -0.06
    importe
    -0.06
    ầm
    -0.06
    gw
    -0.06
    QUIT
    -0.06
     oku
    -0.06
    qc
    -0.06
    illiseconds
    -0.06
    POSITIVE LOGITS
     entire
    0.07
    AMAGE
    0.07
    ãģ¾ãģ£ãģŁ
    0.07
     longest
    0.07
    oot
    0.07
    _fwd
    0.07
    Ñĥв
    0.07
     μην
    0.06
    uten
    0.06
    zek
    0.06
    Activations Density 0.017%

    No Known Activations