© 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. 61014
    Prev
    Next
    INDEX
    Explanations

    references to USB data cables and their functionalities

    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
    .masks
    -0.07
    oren
    -0.06
    ams
    -0.06
    .rt
    -0.06
    yro
    -0.06
    pai
    -0.06
    èįī
    -0.06
    etim
    -0.06
    اعÙĬ
    -0.06
    CU
    -0.06
    POSITIVE LOGITS
     transfer
    0.12
     Transfer
    0.11
    transfer
    0.11
     transfers
    0.11
     transferred
    0.10
    -transfer
    0.10
    Transfer
    0.10
     transferring
    0.10
    _transfer
    0.10
    _TRANSFER
    0.09
    Activations Density 0.038%

    No Known Activations