© 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. 27486
    Prev
    Next
    INDEX
    Explanations

    references to technology and innovation

    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
    egra
    -0.06
     ξά
    -0.05
    thouse
    -0.05
     Nest
    -0.05
    urr
    -0.05
    thesis
    -0.05
    oser
    -0.05
    agger
    -0.05
     Worse
    -0.05
    ideo
    -0.05
    POSITIVE LOGITS
     general
    0.25
     overall
    0.23
     generally
    0.23
    general
    0.22
    overall
    0.20
     geral
    0.20
     général
    0.19
     вообÑīе
    0.19
    -general
    0.19
     Generally
    0.18
    Activations Density 0.196%

    No Known Activations