© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 56924
    Prev
    Next
    INDEX
    Explanations

    terms related to home design and online shopping for home goods

    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
    idge
    -0.07
    erves
    -0.07
    Requires
    -0.07
    eres
    -0.07
    enny
    -0.07
    ervers
    -0.07
    sis
    -0.07
    á»ĭch
    -0.07
    ypress
    -0.06
    innen
    -0.06
    POSITIVE LOGITS
    ;amp
    0.07
     aud
    0.06
     Idea
    0.06
    strcasecmp
    0.06
     Ideas
    0.06
    екÑģи
    0.06
     ideas
    0.06
     jot
    0.06
    è¹
    0.06
    ``↵
    0.06
    Activations Density 0.000%

    No Known Activations