© 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. 75523
    Prev
    Next
    INDEX
    Explanations

    references to tax-related conditions and criteria

    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
    /*č↵
    -0.09
    {{{
    -0.09
    dlg
    -0.08
    å®ħ
    -0.08
    atÃŃm
    -0.07
    @testable
    -0.07
    âng
    -0.07
    arias
    -0.07
    otel
    -0.07
     ("-
    -0.07
    POSITIVE LOGITS
    eldorf
    0.07
    antz
    0.07
    uner
    0.06
     followed
    0.06
     Robbins
    0.06
    perms
    0.06
     conclusion
    0.05
    0.05
     Mond
    0.05
    nas
    0.05
    Activations Density 0.014%

    No Known Activations