© 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. 54532
    Prev
    Next
    INDEX
    Explanations

    references to the League of Nations and its context in historical discussions

    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
    enko
    -0.08
    _VC
    -0.07
    shed
    -0.07
    å³
    -0.07
    warts
    -0.07
    ogne
    -0.07
    .hw
    -0.06
    -pressure
    -0.06
    :<?
    -0.06
     nghiá»ĩm
    -0.06
    POSITIVE LOGITS
    ouch
    0.07
    acz
    0.06
    uch
    0.06
     dot
    0.06
    TypeInfo
    0.06
    .www
    0.06
     dots
    0.06
    uchs
    0.06
     honour
    0.06
    -confirm
    0.06
    Activations Density 0.008%

    No Known Activations