© 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. 74368
    Prev
    Next
    INDEX
    Explanations

    conversational updates and announcements

    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
     factual
    -0.06
     formerly
    -0.06
     compet
    -0.05
     Beyond
    -0.05
    azing
    -0.05
     Weiner
    -0.05
     separating
    -0.05
    155
    -0.05
     themselves
    -0.05
     k
    -0.05
    POSITIVE LOGITS
    istrovstvÃŃ
    0.12
    å¿Ļ
    0.10
    ãģĵãĤĵãģ«ãģ¡ãģ¯
    0.09
    imd
    0.09
     průbÄĽhu
    0.09
     оÑĩеÑĢед
    0.09
     âĢª
    0.09
    klä
    0.09
    elp
    0.09
    CTYPE
    0.09
    Activations Density 0.008%

    No Known Activations