© 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. 130491
    Prev
    Next
    INDEX
    Explanations

    concepts related to the duality of experiences, particularly contrasting good and bad scenarios

    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
    hya
    -0.07
    anon
    -0.07
    ÅŁk
    -0.07
    ollapsed
    -0.07
    acam
    -0.07
    ä»ģ
    -0.06
    ULA
    -0.06
    ilty
    -0.06
    親
    -0.06
     &#
    -0.06
    POSITIVE LOGITS
    ERRU
    0.08
    åĨĨ
    0.07
    lick
    0.07
    AFX
    0.06
    cxx
    0.06
    arem
    0.06
    ulings
    0.06
    spot
    0.06
    eton
    0.06
    emoc
    0.05
    Activations Density 0.001%

    No Known Activations