© 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. 127070
    Prev
    Next
    INDEX
    Explanations

    source code or programming-related terms

    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
    ÂĨ
    -0.08
     <<-
    -0.07
    Banner
    -0.07
    /books
    -0.07
    ulen
    -0.07
    quires
    -0.06
    otty
    -0.06
    antom
    -0.06
    iger
    -0.06
    PN
    -0.06
    POSITIVE LOGITS
     Mann
    0.06
    inar
    0.06
    jango
    0.06
     Stam
    0.06
    ãĥ³ãĥĩãĤ£
    0.06
    ire
    0.06
    summ
    0.06
     time
    0.06
     django
    0.06
    redi
    0.06
    Activations Density 0.001%

    No Known Activations