© 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. 76538
    Prev
    Next
    INDEX
    Explanations

    terms related to airline loyalty programs and earning rewards

    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
    urus
    -0.07
    /free
    -0.07
     claims
    -0.07
     claim
    -0.06
    claims
    -0.06
    marvin
    -0.06
    redient
    -0.06
    onic
    -0.06
    urst
    -0.06
    ÃŃsk
    -0.06
    POSITIVE LOGITS
     purchases
    0.09
     spends
    0.07
     spend
    0.07
     purchase
    0.07
     lòng
    0.07
     patron
    0.07
    íķĺìĭľ
    0.06
    ãĥ¼ãĥį
    0.06
    ª
    0.06
     spending
    0.06
    Activations Density 0.015%

    No Known Activations