© 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. 15-LLAMASCOPE-RES-131K
    11. 27117
    Prev
    Next
    INDEX
    Explanations

    references to gifts and birthday celebrations

    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
    inton
    -0.07
     Ud
    -0.07
    _ud
    -0.07
    ruh
    -0.06
    #
    -0.06
    tery
    -0.06
    antz
    -0.06
    ÑĥзÑĭ
    -0.06
    @testable
    -0.06
    udy
    -0.06
    POSITIVE LOGITS
     children
    0.16
     kids
    0.13
     child
    0.13
    children
    0.13
     Children
    0.12
     CHILD
    0.12
    .children
    0.12
    Children
    0.11
    (children
    0.11
     niños
    0.11
    Activations Density 0.060%

    No Known Activations