© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 22-LLAMASCOPE-RES-131K
    11. 3586
    Prev
    Next
    INDEX
    Explanations

    key phrases related to business acquisitions and sales, particularly in bankruptcy contexts

    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
    bourg
    -0.08
    omik
    -0.08
    CHASE
    -0.08
     jenter
    -0.07
    akis
    -0.07
    APON
    -0.07
     gratuits
    -0.07
     liá»ĩu
    -0.07
     meis
    -0.07
    ÑĢаÑĤ
    -0.07
    POSITIVE LOGITS
     buyer
    0.19
     buyers
    0.18
     purchaser
    0.15
     Buyer
    0.15
    buyer
    0.14
     Buyers
    0.14
    Buy
    0.14
     purchasers
    0.13
    -buy
    0.13
    buy
    0.12
    Activations Density 0.031%

    No Known Activations