© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 103250
    Prev
    Next
    INDEX
    Explanations

    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
     ragaz
    -0.07
    eras
    -0.07
     ”↵↵
    -0.07
    ormsg
    -0.07
    ëijĺ
    -0.07
    orton
    -0.07
    orex
    -0.06
    rst
    -0.06
    isphere
    -0.06
     Ãľn
    -0.06
    POSITIVE LOGITS
    otle
    0.07
    ']!='
    0.06
    itz
    0.06
    onto
    0.06
    staw
    0.06
    RECT
    0.06
    eut
    0.06
    gent
    0.06
    anges
    0.06
    plet
    0.06
    Activations Density 0.034%

    No Known Activations