© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 57974
    Prev
    Next
    INDEX
    Explanations

    expressions of opposition or disagreement with ideas or 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
    raphics
    -0.08
    rys
    -0.07
    bourne
    -0.07
    lion
    -0.07
    åĨ
    -0.07
    /forms
    -0.07
    egend
    -0.07
    poser
    -0.06
    stad
    -0.06
     treff
    -0.06
    POSITIVE LOGITS
    /conf
    0.08
    atham
    0.07
     principles
    0.07
     established
    0.07
     itself
    0.06
     principle
    0.06
    lict
    0.06
     logic
    0.06
     what
    0.06
     accepted
    0.06
    Activations Density 0.019%

    No Known Activations