© 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 EvalsExportsinterp-engineNEWAPI 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. 73418
    Prev
    Next
    INDEX
    Explanations

    rhetorical questions regarding decisions and outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Question marks and surrounding tokens in rhetorical questions that are often followed by their own answers.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    olan
    -0.07
    istes
    -0.07
    iste
    -0.07
     conserv
    -0.07
    asan
    -0.07
    ви
    -0.07
    θή
    -0.07
    gnu
    -0.06
     Conserv
    -0.06
    est
    -0.06
    POSITIVE LOGITS
     Nope
    0.23
    åIJ¦
    0.11
     नह
    0.11
     FALSE
    0.10
     neither
    0.10
     нÑĸ
    0.10
     false
    0.09
     nor
    0.09
    FALSE
    0.09
    (false
    0.09
    Activations Density 0.017%

    No Known Activations