© 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. 105863
    Prev
    Next
    INDEX
    Explanations

    the phrase "with" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    The word "with" functioning as a preposition that introduces phrases showing relationship, accompaniment, manner, or qualification to preceding information.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    nesty
    -0.07
    éĸ¢ä¿Ĥ
    -0.07
    .templates
    -0.07
    uentes
    -0.07
    esome
    -0.07
    ardy
    -0.07
    ãģ¤ãģij
    -0.07
    adaÅŁ
    -0.07
    uren
    -0.07
    еÑĢÑĤи
    -0.07
    POSITIVE LOGITS
     regard
    0.22
     regards
    0.20
    stood
    0.17
    standing
    0.17
     respect
    0.15
    outh
    0.14
    olding
    0.13
    holds
    0.13
    /by
    0.13
    ering
    0.12
    Activations Density 0.485%

    No Known Activations