© 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. 89572
    Prev
    Next
    INDEX
    Explanations

    interactions and requests related to relationships and companionship

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    alars
    -0.08
     fitte
    -0.08
     queryInterface
    -0.08
    ustin
    -0.08
    oksen
    -0.07
    UTO
    -0.07
    ôn
    -0.07
    _transient
    -0.07
    ienen
    -0.07
    ouden
    -0.07
    POSITIVE LOGITS
     dates
    0.07
     date
    0.07
     Sor
    0.06
     Ney
    0.06
    .rs
    0.06
     join
    0.05
     joined
    0.05
     sor
    0.05
     Sat
    0.05
     next
    0.05
    Activations Density 0.018%

    No Known Activations