© 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. 9-LLAMASCOPE-RES-131K
    6. 95121
    Prev
    Next
    INDEX
    Explanations

    expressions related to patriotism

    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
    ildo
    -0.07
    ERGE
    -0.07
    vez
    -0.07
    íģ¼
    -0.07
    utin
    -0.07
    veis
    -0.07
    oke
    -0.07
     Diablo
    -0.07
    ween
    -0.06
    ieren
    -0.06
    POSITIVE LOGITS
    ously
    0.07
    ischer
    0.07
    elps
    0.07
    ically
    0.06
    -minded
    0.06
    ToLocal
    0.06
    ãĥ³ãĥģ
    0.06
    ische
    0.06
    rophy
    0.06
    ãģĦãģ¾ãģĻ
    0.06
    Activations Density 0.007%

    No Known Activations