© 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. 86512
    Prev
    Next
    INDEX
    Explanations

    references to health and wellness products suitable for various age groups and skin types

    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
    èĩ£
    -0.08
    izen
    -0.07
    illin
    -0.07
    ivor
    -0.06
    æŃ¢
    -0.06
    chor
    -0.06
    zman
    -0.06
    esign
    -0.06
    ple
    -0.06
    emek
    -0.06
    POSITIVE LOGITS
    isma
    0.06
     pronounced
    0.06
     度
    0.06
     busy
    0.06
    å¿Ļ
    0.06
    ullan
    0.06
     misuse
    0.06
    ittel
    0.06
     Tanner
    0.06
    pray
    0.06
    Activations Density 0.007%

    No Known Activations