© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 62917
    Prev
    Next
    INDEX
    Explanations

    phrases that denote clarification or explanation

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

    The token "by" is used primarily to introduce explanations or clarifications of terms, particularly in formal writing and academic contexts, often in phrases like "what I mean by" or to attribute or indicate method.

    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
     reversible
    -0.07
    erken
    -0.07
    ytt
    -0.07
    uns
    -0.06
    >:</
    -0.06
    ãĥ¼ãĤ
    -0.06
    침
    -0.06
    cies
    -0.06
    illy
    -0.06
    ãĥ«ãĤ¯
    -0.06
    POSITIVE LOGITS
     by
    0.16
    by
    0.12
    .by
    0.12
     By
    0.12
    _by
    0.12
    By
    0.11
     oleh
    0.11
     meaning
    0.10
    -by
    0.10
    meaning
    0.10
    Activations Density 0.083%

    No Known Activations