© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 87214
    Prev
    Next
    INDEX
    Explanations

    words related to editing or modifying 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
    igen
    -0.07
    ernals
    -0.07
     depressing
    -0.06
     BaseService
    -0.06
    istr
    -0.06
    dere
    -0.06
    sWith
    -0.06
    ç°
    -0.06
     büy
    -0.06
    empo
    -0.06
    POSITIVE LOGITS
    kaar
    0.07
    reno
    0.07
     Huss
    0.07
    iyon
    0.06
    toolbox
    0.06
    roit
    0.06
    Shape
    0.06
    anium
    0.06
    ArrayType
    0.06
    ting
    0.06
    Activations Density 0.001%

    No Known Activations