© 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. 107645
    Prev
    Next
    INDEX
    Explanations

    references to data structure classes in programming, particularly collections

    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
    .Parcelable
    -0.08
    alse
    -0.07
    utsch
    -0.07
    ÑĢаг
    -0.07
    bedo
    -0.07
    ndata
    -0.06
    íŀĪ
    -0.06
    lingen
    -0.06
    _Context
    -0.06
    anou
    -0.06
    POSITIVE LOGITS
    ei
    0.08
    antz
    0.06
    artic
    0.06
    ãĤ§
    0.06
    pong
    0.06
    eil
    0.06
     wildlife
    0.06
    ÑĢÑĸÑĩ
    0.06
    ej
    0.06
    ãĥ£
    0.06
    Activations Density 0.000%

    No Known Activations