© 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. 73987
    Prev
    Next
    INDEX
    Explanations

    references to demographic groups and statistical data

    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
     Middleton
    -0.09
    /Runtime
    -0.07
    'gc
    -0.07
     past
    -0.07
    ãĤ¿ãĥ³
    -0.06
    uum
    -0.06
    sms
    -0.06
     th
    -0.06
    scan
    -0.06
    echa
    -0.06
    POSITIVE LOGITS
     Benton
    0.06
    zim
    0.06
    em
    0.06
    apon
    0.06
    nets
    0.06
    net
    0.06
    adget
    0.06
    alar
    0.06
     Há»ĵ
    0.06
    маг
    0.06
    Activations Density 0.000%

    No Known Activations