© 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. 71203
    Prev
    Next
    INDEX
    Explanations

    numerical data and references to formal grievances

    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
    füg
    -0.08
     Yüz
    -0.07
    isser
    -0.07
    resolver
    -0.07
     миÑĤ
    -0.07
     satisf
    -0.06
    UPI
    -0.06
    ä¾
    -0.06
    issement
    -0.06
    .freeze
    -0.06
    POSITIVE LOGITS
    imu
    0.07
    0.07
    mdi
    0.07
     precisely
    0.06
    ynes
    0.06
     exactly
    0.06
     ode
    0.06
     Hamp
    0.06
     ï¿¥
    0.06
    MUX
    0.05
    Activations Density 0.000%

    No Known Activations