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

    Neuronpedia

    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. 118256
    Prev
    Next
    INDEX
    Explanations

    recurring instances of the word "to" in various contexts

    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
    attery
    -0.08
    instanc
    -0.08
    luetooth
    -0.07
     Už
    -0.07
    òng
    -0.07
     دÙģ
    -0.07
    illance
    -0.07
    ÑĢива
    -0.07
    Multiply
    -0.07
    ÏĤ
    -0.07
    POSITIVE LOGITS
    upply
    0.06
     favor
    0.06
    ur
    0.06
    aside
    0.06
     favors
    0.06
    opol
    0.06
    oss
    0.06
     Tus
    0.06
    iv
    0.06
     supply
    0.06
    Activations Density 0.015%

    No Known Activations