© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 60667
    Prev
    Next
    INDEX
    Explanations

    references to various forms of nationalism, supremacy, and political ideologies

    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
    aan
    -0.07
    ofire
    -0.07
    istrovstvÃŃ
    -0.07
    sz
    -0.07
    lek
    -0.06
    oretical
    -0.06
    onym
    -0.06
    licate
    -0.06
    phere
    -0.06
    ein
    -0.06
    POSITIVE LOGITS
    -transitional
    0.07
    atted
    0.06
     approach
    0.06
    -cons
    0.06
    ulous
    0.06
    ousand
    0.06
    ulumi
    0.06
    ãĥ³ãĥģ
    0.06
    isode
    0.06
    type
    0.06
    Activations Density 0.037%

    No Known Activations