© 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. 17-LLAMASCOPE-RES-131K
    11. 70492
    Prev
    Next
    INDEX
    Explanations

    terms related to the legal and financial industry, especially in the context of representation and transactions

    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
    UNDLE
    -0.08
    ãĤ¤ãĥ¤
    -0.08
    ijken
    -0.07
    ibri
    -0.07
    undle
    -0.07
    leon
    -0.07
    onta
    -0.07
    incer
    -0.07
    hoa
    -0.07
    ungle
    -0.07
    POSITIVE LOGITS
     clients
    0.10
     Clients
    0.10
    Clients
    0.09
    clients
    0.08
     client
    0.07
    _clients
    0.07
     maté
    0.07
    client
    0.06
    orch
    0.06
     Client
    0.06
    Activations Density 0.008%

    No Known Activations