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

    Neuronpedia

    Jacobian LensNEW
    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. 15-LLAMASCOPE-RES-131K
    11. 88809
    Prev
    Next
    INDEX
    Explanations

    phrases and terminology associated with forward-looking statements in financial documents

    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
    PTY
    -0.07
    997
    -0.06
    RACT
    -0.06
     Gaw
    -0.06
    attribute
    -0.06
    iations
    -0.06
    inary
    -0.06
    nict
    -0.06
    357
    -0.06
    ÙĪÙħÛĮ
    -0.06
    POSITIVE LOGITS
     Granite
    0.07
    thic
    0.07
    /rss
    0.06
    вÑĢоп
    0.06
     gran
    0.06
    ãĤ¤ãĥī
    0.06
     camp
    0.06
     ÎĬ
    0.06
    éĹª
    0.06
     bras
    0.06
    Activations Density 0.001%

    No Known Activations