© 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. 56591
    Prev
    Next
    INDEX
    Explanations

    terms related to pricing and cost competitiveness

    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
    959
    -0.07
     Bris
    -0.07
    iera
    -0.06
    بÙĬØ©
    -0.06
    vier
    -0.06
    ìĿµ
    -0.06
    crest
    -0.06
    wig
    -0.06
    awe
    -0.06
    imiter
    -0.06
    POSITIVE LOGITS
     prices
    0.08
     price
    0.08
    prices
    0.08
     Moo
    0.07
    ä¾¡æł¼
    0.07
     Rays
    0.07
    price
    0.07
     priced
    0.07
     pricing
    0.07
    PRICE
    0.06
    Activations Density 0.002%

    No Known Activations