© 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 EvalsExportsinterp-engineNEWAPI 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. 72342
    Prev
    Next
    INDEX
    Explanations

    phrases related to data serialization and object representation 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
    acy
    -0.07
    ियत
    -0.07
     Rich
    -0.06
     lem
    -0.06
    arn
    -0.06
    avel
    -0.06
    Views
    -0.06
    è
    -0.06
    BS
    -0.06
     Bust
    -0.06
    POSITIVE LOGITS
    'gc
    0.07
    illet
    0.07
     omas
    0.07
    pong
    0.06
    BTTagCompound
    0.06
    andest
    0.06
    CartItem
    0.06
    ÃŃn
    0.06
    kuk
    0.06
     znam
    0.06
    Activations Density 0.017%

    No Known Activations