© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 125134
    Prev
    Next
    INDEX
    Explanations

    items that indicate artistic contributions or collaborations

    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
     Kil
    -0.06
     Asia
    -0.06
    nel
    -0.05
    usercontent
    -0.05
    ylko
    -0.05
    :UIControl
    -0.05
    MouseButton
    -0.05
    assa
    -0.05
     kil
    -0.05
    oders
    -0.05
    POSITIVE LOGITS
    OCKET
    0.08
    AFX
    0.07
     anale
    0.07
    (åľŁ
    0.07
    gons
    0.07
    /favicon
    0.07
    746
    0.07
    isOk
    0.07
    /query
    0.07
    AndView
    0.07
    Activations Density 0.002%

    No Known Activations