© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 126041
    Prev
    Next
    INDEX
    Explanations

    content related to travel rewards and loyalty programs

    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
    nio
    -0.06
    itchens
    -0.06
    elmet
    -0.06
    .vocab
    -0.06
     onFinish
    -0.06
    iful
    -0.06
    udiant
    -0.06
    dyby
    -0.06
    ingham
    -0.06
    815
    -0.06
    POSITIVE LOGITS
    ango
    0.07
    สะ
    0.07
     rewards
    0.07
     accum
    0.06
    xb
    0.06
    樹
    0.06
     Rewards
    0.06
    åŁ
    0.06
     Smy
    0.06
    activated
    0.06
    Activations Density 0.016%

    No Known Activations