© 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. 129638
    Prev
    Next
    INDEX
    Explanations

    references to initial consultations and processes related to legal or formal agreements

    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
    venida
    -0.06
    zon
    -0.06
    amp
    -0.06
    èªł
    -0.06
    ÙĨÙĩ
    -0.06
    æľį
    -0.06
    _CURRENT
    -0.05
    olph
    -0.05
     currently
    -0.05
     pil
    -0.05
    POSITIVE LOGITS
     usually
    0.11
    usually
    0.10
     Usually
    0.10
    Usually
    0.09
     typically
    0.09
     often
    0.08
     some
    0.08
    éĢļ常
    0.08
     companies
    0.08
     generally
    0.08
    Activations Density 0.037%

    No Known Activations