© 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. 340
    Prev
    Next
    INDEX
    Explanations

    references to online games and discussions about technology

    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
    odzi
    -0.06
     consumer
    -0.06
    jem
    -0.06
     Measurements
    -0.06
     LSM
    -0.05
     measurements
    -0.05
     gsl
    -0.05
     Cic
    -0.05
    ucht
    -0.05
    APS
    -0.05
    POSITIVE LOGITS
     binh
    0.07
    ENTA
    0.07
    ippo
    0.07
    compan
    0.07
     meis
    0.07
    ngen
    0.07
    arrant
    0.07
    LineColor
    0.07
    ĽĪ
    0.06
    IMPLEMENT
    0.06
    Activations Density 0.004%

    No Known Activations