© 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. 5-LLAMASCOPE-RES-131K
    11. 125661
    Prev
    Next
    INDEX
    Explanations

    references to "boutique" or boutique-related concepts

    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
    bra
    -0.08
    ledo
    -0.07
    414
    -0.06
    ibel
    -0.06
    ingle
    -0.06
    667
    -0.06
     apart
    -0.06
    ñ
    -0.06
    632
    -0.06
    akan
    -0.06
    POSITIVE LOGITS
    íĴĪ
    0.07
    edback
    0.07
    ivi
    0.07
     sapi
    0.07
    ÑģÑıÑĤ
    0.06
    GLOSS
    0.06
    APO
    0.06
     Sabha
    0.06
    .GroupBox
    0.06
    iox
    0.06
    Activations Density 0.001%

    No Known Activations