© 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. 17-LLAMASCOPE-RES-131K
    6. 61661
    Prev
    Next
    INDEX
    Explanations

    mentions of people or groups in a friendly or inclusive tone

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

    Terms of address used in greetings to directly address an audience, typically following words like "Hi," "Hello," or "Hey."

    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
    eb
    -0.07
    aland
    -0.07
    _ctor
    -0.07
     Bravo
    -0.06
    eor
    -0.06
    achat
    -0.06
    ibbon
    -0.06
    ucha
    -0.06
    ria
    -0.06
    aÄį
    -0.06
    POSITIVE LOGITS
    opsis
    0.06
    (?:
    0.06
    Currency
    0.06
    ħn
    0.06
     Teddy
    0.06
    yo
    0.06
     Cách
    0.06
    iset
    0.06
    urm
    0.06
     Müz
    0.06
    Activations Density 0.004%

    No Known Activations