© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 95250
    Prev
    Next
    INDEX
    Explanations

    phrases related to legislation and administrative processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    bjerg
    -0.06
    kop
    -0.06
    /tos
    -0.06
    ibri
    -0.06
    kor
    -0.06
    isper
    -0.06
     rough
    -0.06
    anela
    -0.06
    antd
    -0.06
    Fallback
    -0.06
    POSITIVE LOGITS
    ëį°ìĿ´íĬ¸
    0.06
    anded
    0.06
    -breaking
    0.06
    uge
    0.06
    ần
    0.06
    acyj
    0.06
    yen
    0.06
    éĻµ
    0.06
    odium
    0.06
    akit
    0.06
    Activations Density 0.175%

    No Known Activations