© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 41192
    Prev
    Next
    INDEX
    Explanations

    terms related to academic and professional qualifications or affiliations

    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
    pedia
    -0.07
    eydi
    -0.06
    nameof
    -0.06
    ÑĢг
    -0.06
     çĻ¼
    -0.06
    ekim
    -0.06
    UND
    -0.06
    ساس
    -0.06
    âĢº
    -0.06
    IPA
    -0.06
    POSITIVE LOGITS
    ä¹ĭä¸Ģ
    0.07
     (%)
    0.07
    phans
    0.06
    åıĬåħ¶
    0.06
    ÂĿ
    0.06
     Ibid
    0.06
    mes
    0.06
     поб
    0.05
    eron
    0.05
    isme
    0.05
    Activations Density 0.036%

    No Known Activations