© 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. 79501
    Prev
    Next
    INDEX
    Explanations

    action words related to customer notifications and changes in services

    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
    kir
    -0.07
    std
    -0.07
     eb
    -0.06
    ÑĢоÑģÑĤ
    -0.06
    gel
    -0.06
     rub
    -0.06
    hausen
    -0.06
     development
    -0.06
     reson
    -0.06
    affer
    -0.05
    POSITIVE LOGITS
    mour
    0.09
    transition
    0.09
     transition
    0.09
     Migration
    0.09
     affected
    0.09
     migrate
    0.09
     migration
    0.08
    Affected
    0.08
    _migration
    0.08
    Migration
    0.08
    Activations Density 0.027%

    No Known Activations