© 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. 85473
    Prev
    Next
    INDEX
    Explanations

    phrases related to manual processes and physical movements

    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
    .orange
    -0.08
    ικα
    -0.07
    ÈĽ
    -0.07
    νη
    -0.07
    orca
    -0.07
    pta
    -0.07
    pector
    -0.07
    .hwp
    -0.07
    ÑĢаÑĩ
    -0.07
    RuntimeObject
    -0.07
    POSITIVE LOGITS
     transfer
    0.25
     Transfer
    0.23
    transfer
    0.23
     transfers
    0.21
     transferring
    0.21
     transferred
    0.21
    Transfer
    0.21
    -transfer
    0.20
    TRANSFER
    0.18
    .transfer
    0.18
    Activations Density 0.106%

    No Known Activations