© 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. 78437
    Prev
    Next
    INDEX
    Explanations

    instances of the word "flee" or its variations, indicating escape or flight 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
    eum
    -0.07
    frei
    -0.07
     poil
    -0.07
    oe
    -0.06
     (;;)
    -0.06
    .UnitTesting
    -0.06
    ofday
    -0.06
    outs
    -0.06
    izations
    -0.06
    xing
    -0.06
    POSITIVE LOGITS
     khá»ıi
    0.10
    0.07
    zik
    0.07
    omen
    0.06
    ت
    0.06
    entlich
    0.06
    504
    0.06
    pond
    0.06
    .references
    0.06
    kul
    0.06
    Activations Density 0.005%

    No Known Activations