© 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. 129704
    Prev
    Next
    INDEX
    Explanations

    formal legal or contractual language

    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
    ILLA
    -0.06
    νια
    -0.06
    ær
    -0.06
    ubi
    -0.06
    adal
    -0.06
     sqr
    -0.06
    lement
    -0.05
    azzi
    -0.05
     inst
    -0.05
    pl
    -0.05
    POSITIVE LOGITS
     AGRE
    0.08
     Agreement
    0.07
    .RunWith
    0.07
    ìĦŃ
    0.07
    (each
    0.07
     agrees
    0.07
    ABCDEFG
    0.07
    agree
    0.07
     agreed
    0.07
    addtogroup
    0.07
    Activations Density 0.006%

    No Known Activations