© 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. 120200
    Prev
    Next
    INDEX
    Explanations

    information related to document access statistics

    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
    Ŀ
    -0.08
    uez
    -0.07
    western
    -0.06
    DataStream
    -0.06
    енка
    -0.06
    etti
    -0.06
    876
    -0.06
     Arbit
    -0.06
    оли
    -0.06
     Innoc
    -0.05
    POSITIVE LOGITS
    zik
    0.07
    rias
    0.07
    lient
    0.07
     à¤ħद
    0.06
    .normal
    0.06
    allas
    0.06
    ãĥ¼ãĥį
    0.06
    <quote
    0.06
    folios
    0.06
    arma
    0.06
    Activations Density 0.003%

    No Known Activations