© 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. 105424
    Prev
    Next
    INDEX
    Explanations

    references to media and television, particularly regarding artists and Jewish identity

    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
    orks
    -0.08
    azen
    -0.07
    vu
    -0.07
    ometr
    -0.07
    Ĭ
    -0.07
    ableView
    -0.07
    cliffe
    -0.07
    onga
    -0.07
     opc
    -0.07
     Ñĥз
    -0.07
    POSITIVE LOGITS
     itself
    0.08
     independ
    0.07
     vice
    0.07
     complementary
    0.07
     directly
    0.06
     merely
    0.06
    Independ
    0.06
    parate
    0.06
     opposite
    0.06
    andalone
    0.06
    Activations Density 0.048%

    No Known Activations