© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 9-LLAMASCOPE-RES-131K
    11. 96543
    Prev
    Next
    INDEX
    Explanations

    programming symbols and identifiers

    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
    ække
    -0.08
    reon
    -0.08
    deniz
    -0.07
    untas
    -0.07
    usercontent
    -0.07
    rug
    -0.07
    centroid
    -0.07
    ibur
    -0.07
    469
    -0.07
    Disallow
    -0.07
    POSITIVE LOGITS
    ahl
    0.06
     CreateMap
    0.06
    DITION
    0.06
     Mits
    0.06
    inos
    0.06
    ets
    0.06
    uers
    0.05
    lings
    0.05
    urtle
    0.05
    uem
    0.05
    Activations Density 0.109%

    No Known Activations