© 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. 103180
    Prev
    Next
    INDEX
    Explanations

    references to inheritance or superclass methods in programming code

    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
    azzi
    -0.07
    Úĺ
    -0.07
     Seznam
    -0.06
    .MixedReality
    -0.06
    isd
    -0.06
    weeted
    -0.06
    alon
    -0.06
    .CustomButton
    -0.06
    usc
    -0.06
    endencies
    -0.06
    POSITIVE LOGITS
    219
    0.07
    ihan
    0.06
    host
    0.06
    ritel
    0.06
    esome
    0.06
    448
    0.06
    617
    0.06
    reset
    0.06
    404
    0.06
    engu
    0.06
    Activations Density 0.001%

    No Known Activations