© 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. 56946
    Prev
    Next
    INDEX
    Explanations

    specific forms of negation and auxiliary verbs

    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
    inet
    -0.07
    adam
    -0.06
    638
    -0.06
    afi
    -0.06
    639
    -0.06
    ishops
    -0.06
    HEMA
    -0.06
    anim
    -0.06
    owski
    -0.06
    ip
    -0.06
    POSITIVE LOGITS
     à¹Ĩ
    0.08
     theater
    0.07
     gray
    0.07
     traveler
    0.06
     Californ
    0.06
     defenseman
    0.06
     endeavor
    0.06
     Theater
    0.06
     Modeling
    0.06
    पत
    0.06
    Activations Density 0.002%

    No Known Activations