© 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. 88653
    Prev
    Next
    INDEX
    Explanations

    terms associated with load and loading processes

    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
    翼
    -0.07
     Bucc
    -0.06
    und
    -0.06
    asive
    -0.06
    /left
    -0.06
    panic
    -0.06
    osy
    -0.06
    assen
    -0.06
    abad
    -0.06
    AGO
    -0.06
    POSITIVE LOGITS
    Unload
    0.10
    ings
    0.10
    -bearing
    0.09
    rant
    0.09
    edImage
    0.09
    icrous
    0.08
    frey
    0.08
    ControlEvents
    0.08
    ahl
    0.07
    /save
    0.07
    Activations Density 0.022%

    No Known Activations