© 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. 125302
    Prev
    Next
    INDEX
    Explanations

    references to Irish heritage and cultural 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
    ÏĢοÏĤ
    -0.06
    mono
    -0.06
    _SS
    -0.06
    оÑĢи
    -0.06
    /form
    -0.06
     Fundamental
    -0.06
    REW
    -0.06
    UTO
    -0.05
    ãĤĴãģĭ
    -0.05
     ex
    -0.05
    POSITIVE LOGITS
     virtues
    0.09
     achievements
    0.09
     supposedly
    0.09
     accomplishments
    0.08
     allegedly
    0.08
     Ñıк
    0.08
    _stderr
    0.07
     benefits
    0.07
    enef
    0.07
     supposed
    0.07
    Activations Density 0.026%

    No Known Activations