© 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. 120937
    Prev
    Next
    INDEX
    Explanations

    instances of disbelief and sinful behavior

    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
    esh
    -0.06
    kal
    -0.06
     cort
    -0.06
    itag
    -0.06
     mens
    -0.06
    è¡Ĺ
    -0.06
    pon
    -0.06
    _dispatch
    -0.05
    -0.05
    ensation
    -0.05
    POSITIVE LOGITS
    mony
    0.07
    elocity
    0.07
    STYPE
    0.07
    preter
    0.07
    pNet
    0.07
    SCII
    0.07
     kanal
    0.07
    çIJ³
    0.06
    SCI
    0.06
    vine
    0.06
    Activations Density 0.000%

    No Known Activations