© 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. 124247
    Prev
    Next
    INDEX
    Explanations

    key moments indicating the end of a narrative or significant event

    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
    edin
    -0.07
     Chatt
    -0.06
     Forced
    -0.06
    âĢİ
    -0.06
    rex
    -0.06
    Ms
    -0.06
     copp
    -0.06
     Suppress
    -0.06
    Yesterday
    -0.06
     Yesterday
    -0.06
    POSITIVE LOGITS
     mesel
    0.08
    год
    0.07
    -scalable
    0.07
    fone
    0.07
    oire
    0.07
    .mousePosition
    0.07
    ouser
    0.07
    ramework
    0.07
    _mE
    0.07
    ider
    0.07
    Activations Density 0.000%

    No Known Activations