© 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. 17-LLAMASCOPE-RES-131K
    6. 73561
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names associated with individuals or institutions

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

    Identified tokens are parts of proper names, technical terms, or abbreviations that often appear at word boundaries or in code identifiers. They frequently show up in contexts like software documentation, technical specifications, or as parts of person/organization names.

    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
    ,
    -0.06
     vast
    -0.06
     possess
    -0.06
     (
    -0.06
     /
    -0.05
    698
    -0.05
    ennes
    -0.05
    enthal
    -0.05
    ampton
    -0.05
    -
    -0.05
    POSITIVE LOGITS
    soever
    0.09
    ÑįÑĤомÑĥ
    0.09
    phalt
    0.09
    gether
    0.08
    etheless
    0.08
    ORAGE
    0.08
    tlement
    0.08
    _exempt
    0.08
    HING
    0.08
    odore
    0.08
    Activations Density 0.363%

    No Known Activations