© 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. 124923
    Prev
    Next
    INDEX
    Explanations

    comparative phrases and expressions relating to excellence and quality

    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
    onen
    -0.08
    ÙģÙĩ
    -0.08
    ä¸įåIJĮ
    -0.07
    ãģĭãĤı
    -0.07
    esi
    -0.06
    änder
    -0.06
    raith
    -0.06
    lili
    -0.06
    LLL
    -0.06
    erdale
    -0.06
    POSITIVE LOGITS
     any
    0.11
     many
    0.09
     even
    0.09
     some
    0.08
     actual
    0.07
     sometimes
    0.07
    ä»»ä½ķ
    0.07
    many
    0.07
     ever
    0.07
     entire
    0.07
    Activations Density 0.023%

    No Known Activations