© 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. 59472
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "package" in technical or coding contexts

    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
    erton
    -0.08
    .googlecode
    -0.07
    cep
    -0.07
    ιÏĥÏĦή
    -0.07
     chiếc
    -0.06
    ednou
    -0.06
    enia
    -0.06
    .SizeType
    -0.06
    olib
    -0.06
    URT
    -0.06
    POSITIVE LOGITS
    IPC
    0.07
    -wide
    0.06
     mates
    0.06
    WG
    0.06
     Leisure
    0.06
     меж
    0.06
    WS
    0.06
    chal
    0.06
    WN
    0.06
    912
    0.06
    Activations Density 0.002%

    No Known Activations