© 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. 17-LLAMASCOPE-RES-131K
    11. 59312
    Prev
    Next
    INDEX
    Explanations

    references to collections and data structures in programming

    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
    iscard
    -0.08
    udeau
    -0.07
    hoo
    -0.07
    ponent
    -0.07
    nets
    -0.07
    emouth
    -0.07
    OOT
    -0.07
    esus
    -0.07
    ickets
    -0.07
    æ´
    -0.06
    POSITIVE LOGITS
     guarante
    0.06
    .range
    0.06
    itude
    0.06
     Rath
    0.06
    ante
    0.06
    ÏĦεί
    0.06
    .ribbon
    0.05
    anko
    0.05
     Brace
    0.05
     dances
    0.05
    Activations Density 0.001%

    No Known Activations