© 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. 53722
    Prev
    Next
    INDEX
    Explanations

    references to out-of-body experiences and the concept of distancing in acting

    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
    elan
    -0.07
    ɵ
    -0.07
    uzzle
    -0.07
    yms
    -0.06
    _kw
    -0.06
    ispecies
    -0.06
    .Bounds
    -0.06
    elib
    -0.06
    catid
    -0.06
     tetas
    -0.06
    POSITIVE LOGITS
     detached
    0.09
     impartial
    0.08
     viewing
    0.07
     critically
    0.07
     observing
    0.07
     perspective
    0.07
    Mana
    0.07
     observe
    0.06
     observation
    0.06
    antage
    0.06
    Activations Density 0.018%

    No Known Activations