© 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. 91779
    Prev
    Next
    INDEX
    Explanations

    questions that prompt introspection or exploration of personal experiences and beliefs

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    otta
    -0.06
    uhe
    -0.06
    859
    -0.06
    argent
    -0.06
    _:*
    -0.06
    onte
    -0.06
    imageName
    -0.06
    ::<
    -0.05
    achten
    -0.05
     havoc
    -0.05
    POSITIVE LOGITS
     does
    0.13
     do
    0.12
     Does
    0.11
     did
    0.10
    does
    0.10
    Does
    0.09
    ells
    0.09
    did
    0.07
    ÑĤаб
    0.07
    _does
    0.07
    Activations Density 0.020%

    No Known Activations