© 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. 126225
    Prev
    Next
    INDEX
    Explanations

    references to controversial medical treatments and related discussions

    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
    Clause
    -0.07
    oji
    -0.07
    à¥įवà¤ļ
    -0.07
    chwitz
    -0.07
    cü
    -0.06
     accommodation
    -0.06
    ENU
    -0.06
    çŃĨ
    -0.06
    ãĥ©ãĤ¹
    -0.06
    ettes
    -0.06
    POSITIVE LOGITS
     experimental
    0.07
     Adler
    0.07
    experimental
    0.07
    strom
    0.07
    protocol
    0.06
    ër
    0.06
    regar
    0.06
     protocol
    0.06
    lijah
    0.06
    iram
    0.06
    Activations Density 0.003%

    No Known Activations