© 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. 131040
    Prev
    Next
    INDEX
    Explanations

    expressions related to zooming and magnification

    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
    wor
    -0.07
    ssp
    -0.06
     vrou
    -0.06
    ิà¹ī
    -0.06
     Palette
    -0.06
    ASC
    -0.06
     ÐŁÑĢод
    -0.06
     Pascal
    -0.06
    ewire
    -0.06
    RAIN
    -0.06
    POSITIVE LOGITS
     zoom
    0.10
    ToFit
    0.09
     ì¤
    0.08
    zoom
    0.08
     Zoom
    0.08
    _zoom
    0.07
     magn
    0.07
    Magn
    0.07
    Zoom
    0.07
    .zoom
    0.07
    Activations Density 0.010%

    No Known Activations