© 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. 26743
    Prev
    Next
    INDEX
    Explanations

    technical terms and references related to programming or web development

    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
     PRESS
    -0.07
    -fw
    -0.07
    ©
    -0.07
    اÛĮØ´
    -0.07
    ÛĮÙĦÛĮ
    -0.07
     Fem
    -0.06
    OfSize
    -0.06
    éĽ²
    -0.06
     ãĤ¢ãĤ¤
    -0.06
     pressing
    -0.06
    POSITIVE LOGITS
    andex
    0.08
    hoot
    0.07
    ><![
    0.07
    alog
    0.07
    ursal
    0.07
    agina
    0.07
    0.06
    ovich
    0.06
    üss
    0.06
    orian
    0.06
    Activations Density 0.001%

    No Known Activations