© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 91630
    Prev
    Next
    INDEX
    Explanations

    Question marks that appear at the end of questions in Q&A contexts, often followed by responses or answers.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219
    Triggered 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
    Negative Logits
    /rs
    -0.07
    ust
    -0.07
    med
    -0.07
    iy
    -0.06
    unny
    -0.06
     signer
    -0.06
    h
    -0.06
    ayer
    -0.06
    lig
    -0.06
     Leaf
    -0.06
    POSITIVE LOGITS
     answer
    0.13
    answer
    0.13
     Answer
    0.12
     ANSW
    0.12
    -answer
    0.11
    Answer
    0.10
     answers
    0.10
    ENARIO
    0.10
    çŃĶ
    0.10
     answered
    0.09
    Activations Density 0.026%

    No Known Activations