© 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. 88362
    Prev
    Next
    INDEX
    Explanations

    large numerical values and financial 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
    esi
    -0.07
    mann
    -0.07
    baugh
    -0.06
    981
    -0.06
    annes
    -0.06
    nak
    -0.06
     Bang
    -0.06
     Goth
    -0.06
    .GroupLayout
    -0.06
    illes
    -0.06
    POSITIVE LOGITS
     threshold
    0.08
     Threshold
    0.08
     thanks
    0.07
     again
    0.07
    again
    0.07
     sooner
    0.07
     Linden
    0.07
    inha
    0.07
    REA
    0.07
    erez
    0.07
    Activations Density 0.016%

    No Known Activations