© 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. 29824
    Prev
    Next
    INDEX
    Explanations

    indicators of coding or programming context in texts

    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
    arest
    -0.07
    .gameserver
    -0.06
     Bulk
    -0.06
    rani
    -0.06
    nk
    -0.06
    pf
    -0.06
    D
    -0.06
    rop
    -0.06
    110
    -0.05
    .scalablytyped
    -0.05
    POSITIVE LOGITS
     California
    0.07
     Californ
    0.07
    California
    0.07
    ILES
    0.07
    ancellable
    0.06
    aklı
    0.06
    omin
    0.06
     ÙĨس
    0.06
    ewis
    0.06
     Calif
    0.06
    Activations Density 0.000%

    No Known Activations