© 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. 15-LLAMASCOPE-RES-131K
    11. 86597
    Prev
    Next
    INDEX
    Explanations

    instances of change and progression in personal experiences or narratives

    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
    má
    -0.08
    одо
    -0.08
    ebp
    -0.08
     dán
    -0.07
     Merk
    -0.07
    olini
    -0.07
    Łèĥ½
    -0.07
    ldb
    -0.07
    exion
    -0.07
    ứ
    -0.07
    POSITIVE LOGITS
     transfer
    0.11
     switch
    0.10
     Transfer
    0.10
     transfers
    0.10
     move
    0.10
    Transfer
    0.10
    transfer
    0.09
     transferred
    0.09
     switched
    0.09
     switching
    0.09
    Activations Density 0.015%

    No Known Activations