© 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. 88363
    Prev
    Next
    INDEX
    Explanations

    instructions related to downloading and setting wallpapers

    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
    ooke
    -0.07
    uml
    -0.06
    usted
    -0.06
    견
    -0.06
    ieran
    -0.06
    æ¢
    -0.06
    /Main
    -0.06
    baseUrl
    -0.06
    onest
    -0.06
    oxid
    -0.06
    POSITIVE LOGITS
    tol
    0.07
    atest
    0.07
    echn
    0.07
    ahl
    0.06
    Sizes
    0.06
    ori
    0.06
    *size
    0.06
     Lam
    0.06
     typealias
    0.06
     ful
    0.06
    Activations Density 0.003%

    No Known Activations