© 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. 56026
    Prev
    Next
    INDEX
    Explanations

    references to creative or artistic endeavors, particularly in comics and their production

    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
     comeback
    -0.06
     dem
    -0.06
     [âĢ¦]
    -0.06
    ì§Ī
    -0.05
     ul
    -0.05
     ti
    -0.05
    ãĥĥ
    -0.05
     en
    -0.05
    TextNode
    -0.05
     Ere
    -0.05
    POSITIVE LOGITS
    iropr
    0.08
    ternet
    0.08
    ccb
    0.08
    armacy
    0.08
    bject
    0.08
    osterone
    0.08
    .Skin
    0.07
    errick
    0.07
    ernote
    0.07
    fdc
    0.07
    Activations Density 0.042%

    No Known Activations