© 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 EvalsExportsinterp-engineNEWAPI 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. 104692
    Prev
    Next
    INDEX
    Explanations

    the word "so" in various contexts and its usage in sentences

    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
    addir
    -0.08
    íį¼
    -0.07
    ¤¤
    -0.07
    ãĤĵãģ©
    -0.07
    andre
    -0.07
    пон
    -0.07
    celed
    -0.07
    arti
    -0.07
    tainment
    -0.07
    tha
    -0.07
    POSITIVE LOGITS
     thus
    0.09
    thus
    0.07
     thereby
    0.07
     basically
    0.06
    ATO
    0.06
    522
    0.06
     wiÄĻc
    0.06
    oret
    0.06
     knew
    0.06
     Thus
    0.06
    Activations Density 0.033%

    No Known Activations