Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 95904
    Prev
    Next
    INDEX
    Explanations

    phrases related to discussions of ethical and social issues

    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
    angu
    -0.07
    ransition
    -0.07
    mark
    -0.07
    inkel
    -0.06
    izo
    -0.06
    lings
    -0.06
    pty
    -0.06
    iyim
    -0.06
    odynam
    -0.06
    alla
    -0.06
    POSITIVE LOGITS
    âĢĮâĢĮ
    0.07
     actively
    0.07
    yped
    0.06
    aben
    0.06
     root
    0.06
    unfold
    0.06
    .pb
    0.06
     Benn
    0.06
     Ùĥس
    0.06
    عات
    0.06
    Activations Density 0.061%

    No Known Activations