© 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. 57318
    Prev
    Next
    INDEX
    Explanations

    keywords related to color and texture processing in images

    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
    gren
    -0.07
    ãĥĥãĥĦ
    -0.07
    /sn
    -0.06
    teg
    -0.06
    hatt
    -0.06
    anela
    -0.06
    iked
    -0.06
    ÏħÏĩ
    -0.06
    ONGO
    -0.06
    anel
    -0.06
    POSITIVE LOGITS
     gradients
    0.09
     gradient
    0.08
    ầu
    0.07
     Gradient
    0.07
    gradient
    0.07
    -gradient
    0.07
    Ģë¡ľ
    0.07
    Gradient
    0.06
    dle
    0.06
    _sw
    0.06
    Activations Density 0.000%

    No Known Activations