© 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. 118450
    Prev
    Next
    INDEX
    Explanations

    words related to cautionary statements or alerts

    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
    /by
    -0.06
    mos
    -0.06
    alam
    -0.06
     Ale
    -0.06
    /from
    -0.06
    gu
    -0.06
    ien
    -0.06
     Buckley
    -0.06
    an
    -0.05
    ucha
    -0.05
    POSITIVE LOGITS
    ingly
    0.08
    ļĮ
    0.08
    exion
    0.08
    374
    0.07
    TOTYPE
    0.07
    -about
    0.07
     rằng
    0.07
    eware
    0.07
     Danger
    0.07
    APPER
    0.07
    Activations Density 0.004%

    No Known Activations