© 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. 120735
    Prev
    Next
    INDEX
    Explanations

    references to credibility and dishonesty in testimonies or accounts

    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
    ->__
    -0.07
    undler
    -0.07
    rowsable
    -0.07
    enz
    -0.07
    ARGIN
    -0.07
    "label
    -0.07
    anou
    -0.07
     Mitar
    -0.07
    enson
    -0.07
    alom
    -0.07
    POSITIVE LOGITS
     credibility
    0.09
     witness
    0.07
     credible
    0.06
    cred
    0.06
     ver
    0.06
     witnesses
    0.06
     lies
    0.06
     versus
    0.06
    credible
    0.06
    mos
    0.06
    Activations Density 0.035%

    No Known Activations