© 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. 80780
    Prev
    Next
    INDEX
    Explanations

    the conjunction "and" used in various contexts

    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
    /stretch
    -0.08
    regnum
    -0.08
    odus
    -0.08
    illance
    -0.08
    ulo
    -0.08
    istrovstvÃŃ
    -0.07
    нод
    -0.07
    ebe
    -0.07
    LBL
    -0.07
    posix
    -0.07
    POSITIVE LOGITS
    xdc
    0.06
    fish
    0.06
    .
    0.06
    ativ
    0.06
     ----------------------------------------------------------------------------↵
    0.05
     Verfüg
    0.05
    323
    0.05
    edic
    0.05
    305
    0.05
     Discover
    0.05
    Activations Density 0.000%

    No Known Activations