© 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. 30201
    Prev
    Next
    INDEX
    Explanations

    terms related to file transfer protocols and network configurations

    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
    udden
    -0.08
     mad
    -0.06
     race
    -0.06
     SOS
    -0.06
    appy
    -0.05
    ÏĦÏĮ
    -0.05
     roadside
    -0.05
    DDS
    -0.05
    767
    -0.05
     revenue
    -0.05
    POSITIVE LOGITS
     transfer
    0.09
     transfers
    0.08
     transferring
    0.08
     Transfer
    0.08
    -transfer
    0.08
    TRANSFER
    0.08
    transfer
    0.08
    _transfer
    0.08
     transferred
    0.07
    âĸį
    0.07
    Activations Density 0.016%

    No Known Activations