© 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. 17-LLAMASCOPE-RES-131K
    11. 77177
    Prev
    Next
    INDEX
    Explanations

    conditions and requirements related to tax and legal liabilities

    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
    chter
    -0.06
     if
    -0.06
     dod
    -0.06
     doubly
    -0.05
     Fus
    -0.05
     even
    -0.05
     hopefully
    -0.05
    ion
    -0.05
     funnel
    -0.05
     homo
    -0.05
    POSITIVE LOGITS
    multiple
    0.10
     birden
    0.09
    _Lean
    0.09
    imulator
    0.08
     multiple
    0.08
    Multiple
    0.08
    ultiple
    0.08
    uyên
    0.08
     addCriterion
    0.07
    .GPIO
    0.07
    Activations Density 0.014%

    No Known Activations