© 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. 41826
    Prev
    Next
    INDEX
    Explanations

    references to historical dates and 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
    iem
    -0.07
    edb
    -0.07
    zano
    -0.07
    arendra
    -0.06
    aq
    -0.06
     Bender
    -0.06
    inho
    -0.06
    aft
    -0.06
    emale
    -0.06
    adio
    -0.06
    POSITIVE LOGITS
    cers
    0.08
    mers
    0.07
    دÙĪاج
    0.07
    ature
    0.07
     beginning
    0.07
    cam
    0.07
    iren
    0.07
    ather
    0.07
    tempts
    0.07
    ly
    0.07
    Activations Density 0.005%

    No Known Activations