© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 87887
    Prev
    Next
    INDEX
    Explanations

    forms of the verb "be" and associated phrases indicating states of being or actions

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

    The token "being" and phrases like "be more" or other variations of "be" followed by modifiers indicate instances where someone is expressing a way of behaving or conducting oneself, often suggesting authenticity, honesty, or a particular manner or degree of interaction with others.

    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
     perce
    -0.07
    omik
    -0.06
    iedo
    -0.06
    EDIUM
    -0.06
    aldi
    -0.06
    aj
    -0.06
    .dataTables
    -0.05
     minions
    -0.05
    indered
    -0.05
    .metamodel
    -0.05
    POSITIVE LOGITS
    à¥ģह
    0.07
    ias
    0.07
    IAS
    0.07
     davran
    0.07
    coop
    0.07
    isex
    0.06
    à¹Īวà¸ĩ
    0.06
    pone
    0.06
    neighbor
    0.06
    âΧ
    0.06
    Activations Density 0.056%

    No Known Activations