© 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. 26538
    Prev
    Next
    INDEX
    Explanations

    instances of conflict or contention in personal relationships

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

    Words or phrases describing conflicts, confrontations, or exchanges between people, particularly on social media or in public settings. These include expressions like "shots," "fight," "exchange bitter words," "shade," "lashes out," "respond to insult," "dispute," and "reacts to." Many examples involve celebrities, politicians, or public figures engaged in verbal sparring, Twitter arguments, or feuds.

    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
    annes
    -0.07
    rai
    -0.06
    pard
    -0.06
    енÑĥ
    -0.06
    à¹ģà¸ľ
    -0.06
     Burl
    -0.06
    aris
    -0.06
    omore
    -0.06
    nder
    -0.06
    ÐłÐĺ
    -0.06
    POSITIVE LOGITS
     respond
    0.09
     Respond
    0.08
    Respond
    0.08
     responded
    0.08
     response
    0.08
     responds
    0.07
    respond
    0.07
     retal
    0.07
    response
    0.07
    .respond
    0.07
    Activations Density 0.150%

    No Known Activations