© 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 EvalsExportsAPI 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. 56131
    Prev
    Next
    INDEX
    Explanations

    discussions and analyses surrounding complex social issues

    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
    -0.07
    owo
    -0.07
    eya
    -0.06
     stole
    -0.06
     Sea
    -0.06
     stealing
    -0.06
    ling
    -0.06
    agy
    -0.06
    rud
    -0.06
     for
    -0.06
    POSITIVE LOGITS
    .updateDynamic
    0.08
     webs
    0.08
    ">//
    0.07
    BackingField
    0.07
    webs
    0.07
    :\/\/
    0.07
    Å¡ak
    0.07
    念
    0.07
     actors
    0.07
    èµĸ
    0.07
    Activations Density 0.002%

    No Known Activations