© 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. 89149
    Prev
    Next
    INDEX
    Explanations

    terms related to government and its functions

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

    Key content elements that serve connecting or specifying functions within technical, legal, or programming contexts.

    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
    ansi
    -0.08
    ames
    -0.07
    cms
    -0.06
     Invest
    -0.06
    agnost
    -0.06
    alse
    -0.06
    atz
    -0.06
    ëį°ìĿ´íĬ¸
    -0.06
    atti
    -0.06
    jis
    -0.06
    POSITIVE LOGITS
    èŃ
    0.06
    EndPoint
    0.06
    ewear
    0.06
    tdown
    0.06
    éĿ
    0.06
    ův
    0.06
    .toolbox
    0.06
    -floating
    0.06
    (Arg
    0.06
    isci
    0.06
    Activations Density 0.076%

    No Known Activations