© 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. 84387
    Prev
    Next
    INDEX
    Explanations

    instances of the word "did" in various contexts

    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
    .obtain
    -0.07
     actionTypes
    -0.07
    tract
    -0.07
    isser
    -0.06
    itioner
    -0.06
    969
    -0.06
    ëª
    -0.06
    itom
    -0.06
     sami
    -0.06
     sobie
    -0.06
    POSITIVE LOGITS
     Bark
    0.08
     indeed
    0.06
     followed
    0.06
    Bes
    0.06
    /d
    0.06
    uco
    0.06
    åı
    0.06
    Disk
    0.05
    ube
    0.05
    addon
    0.05
    Activations Density 0.051%

    No Known Activations