© 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. 16157
    Prev
    Next
    INDEX
    Explanations

    price-related information regarding ticket purchasing

    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
     tam
    -0.07
     Tam
    -0.06
    (Display
    -0.06
    avity
    -0.06
     Millions
    -0.06
    idl
    -0.06
    èĤ
    -0.06
     اÙĦÙħÙĨ
    -0.06
    alli
    -0.05
     secrecy
    -0.05
    POSITIVE LOGITS
    جة
    0.08
    doors
    0.07
     seats
    0.07
     concessions
    0.07
     RESERVED
    0.07
     doors
    0.07
     concession
    0.07
    /Gate
    0.07
    åѦçĶŁ
    0.07
     admission
    0.07
    Activations Density 0.010%

    No Known Activations