© 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. 75061
    Prev
    Next
    INDEX
    Explanations

    conditions and operations related to image processing and merging

    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
    progressbar
    -0.07
    xae
    -0.07
    è¬
    -0.07
    dete
    -0.06
    ittest
    -0.06
    ÏĢι
    -0.06
    OPTIONS
    -0.06
    866
    -0.06
    (æľ¨
    -0.06
    (æ°´
    -0.06
    POSITIVE LOGITS
     couldn
    0.07
     attempted
    0.07
    uld
    0.07
     zbyt
    0.07
    ulg
    0.06
    fos
    0.06
    deen
    0.06
    ULD
    0.06
    itage
    0.06
     attempt
    0.06
    Activations Density 0.024%

    No Known Activations