© 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. 106003
    Prev
    Next
    INDEX
    Explanations

    information related to credit card rewards and bonuses

    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
    idders
    -0.08
    _rwlock
    -0.07
    anc
    -0.07
    ç±
    -0.06
    .defer
    -0.06
    ensch
    -0.06
    .googleapis
    -0.06
    utting
    -0.06
    ÎĮ
    -0.06
    ensed
    -0.06
    POSITIVE LOGITS
     card
    0.09
     cards
    0.07
     base
    0.07
     activation
    0.07
     award
    0.06
    card
    0.06
     Base
    0.06
     Chase
    0.06
     mile
    0.06
    CARD
    0.06
    Activations Density 0.005%

    No Known Activations