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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 29998
    Prev
    Next
    INDEX
    Explanations

    information related to discounts and cost-saving opportunities

    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
    éné
    -0.08
    ieten
    -0.07
    yles
    -0.06
    slaught
    -0.06
    isse
    -0.06
    ancellor
    -0.06
    adena
    -0.06
     Reform
    -0.06
    uta
    -0.06
    piel
    -0.06
    POSITIVE LOGITS
     discounts
    0.08
     addCriterion
    0.08
    loy
    0.07
     rewards
    0.07
    á¿
    0.07
     multip
    0.07
    DUCT
    0.06
     reward
    0.06
     loyalty
    0.06
     special
    0.06
    Activations Density 0.010%

    No Known Activations