© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 130490
    Prev
    Next
    INDEX
    Explanations

    instances of the word "so" used to indicate reasoning or conclusions

    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
    azz
    -0.07
    otype
    -0.07
    rou
    -0.07
    idth
    -0.07
    ανδ
    -0.07
    rit
    -0.07
    prav
    -0.07
    hub
    -0.06
    érc
    -0.06
    trs
    -0.06
    POSITIVE LOGITS
     therefore
    0.07
     hence
    0.07
    folio
    0.07
    onen
    0.06
    387
    0.06
     ma
    0.06
    547
    0.06
    maal
    0.06
     Mast
    0.06
     Verm
    0.06
    Activations Density 0.013%

    No Known Activations