© 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. 17-LLAMASCOPE-RES-131K
    11. 87075
    Prev
    Next
    INDEX
    Explanations

    references to programming languages

    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
    lying
    -0.08
    pling
    -0.08
    ager
    -0.08
    ior
    -0.07
    self
    -0.07
    lund
    -0.07
    iqu
    -0.07
    ildo
    -0.07
    /change
    -0.07
    ly
    -0.07
    POSITIVE LOGITS
    auge
    0.08
    assic
    0.08
    hift
    0.08
    .googleapis
    0.08
    OrDefault
    0.07
     franca
    0.07
    ofday
    0.07
    /or
    0.07
    -speaking
    0.07
    оналÑĮ
    0.07
    Activations Density 0.024%

    No Known Activations