© 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. 63291
    Prev
    Next
    INDEX
    Explanations

    expressions of personal reflection and belief

    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
    okus
    -0.06
    ké
    -0.06
    anela
    -0.06
    wa
    -0.06
    inds
    -0.06
    inery
    -0.06
    appe
    -0.06
    arc
    -0.06
     Pou
    -0.06
    hai
    -0.06
    POSITIVE LOGITS
    .scalablytyped
    0.09
    бав
    0.07
     maybe
    0.07
    mux
    0.07
    .bpm
    0.07
    746
    0.07
    BOVE
    0.07
     ÙĬÙĪ
    0.06
     gangbang
    0.06
    AYER
    0.06
    Activations Density 0.024%

    No Known Activations