© 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. 15-LLAMASCOPE-RES-131K
    11. 103142
    Prev
    Next
    INDEX
    Explanations

    sections and organization in academic writing

    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
     worse
    -0.06
    ahun
    -0.06
    otas
    -0.06
    visor
    -0.06
    é¢ĺ
    -0.06
    orp
    -0.06
     Fatal
    -0.06
    ̣
    -0.06
    xin
    -0.06
     Interpret
    -0.06
    POSITIVE LOGITS
     briefly
    0.10
    brief
    0.08
     cÃŃt
    0.08
    InputBorder
    0.08
    WWW
    0.07
    _pci
    0.07
    istrovstvÃŃ
    0.07
    ogui
    0.07
     >",
    0.07
    bsp
    0.07
    Activations Density 0.075%

    No Known Activations