© 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. 84044
    Prev
    Next
    INDEX
    Explanations

    references to dates, particularly in a news context

    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
    jang
    -0.06
    WithContext
    -0.06
    ité
    -0.06
    غر
    -0.06
    ấp
    -0.06
    oref
    -0.06
    mlin
    -0.06
    allen
    -0.06
    edom
    -0.06
    ammen
    -0.06
    POSITIVE LOGITS
    anky
    0.07
    aines
    0.07
     GetMessage
    0.07
    ëĿ¼ëıĦ
    0.07
    toc
    0.06
     ÙħÛĮÙĦادÛĮ
    0.06
    testimonial
    0.06
    utenberg
    0.06
    imiter
    0.06
    oney
    0.06
    Activations Density 0.005%

    No Known Activations