© 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. 69159
    Prev
    Next
    INDEX
    Explanations

    references to emotional struggles and personal challenges

    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
     saya
    -0.08
    ingham
    -0.08
     our
    -0.07
    OMPI
    -0.07
    ollo
    -0.07
     my
    -0.07
    egin
    -0.07
    iland
    -0.07
    emean
    -0.07
    edl
    -0.07
    POSITIVE LOGITS
     hadn
    0.09
     habÃŃa
    0.07
    itted
    0.07
    odox
    0.07
     had
    0.06
    eway
    0.06
    cord
    0.06
    849
    0.06
     avait
    0.06
     himself
    0.06
    Activations Density 0.061%

    No Known Activations