© 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. 118006
    Prev
    Next
    INDEX
    Explanations

    repeated conjunctions, particularly "and," indicating connections between thoughts or subjects

    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
    upo
    -0.07
    OperationException
    -0.07
    Äħd
    -0.07
    umatic
    -0.07
    Enc
    -0.06
    stances
    -0.06
    hesive
    -0.06
    imentary
    -0.06
    ãģĨãģ¡
    -0.06
    äºĮ人
    -0.06
    POSITIVE LOGITS
     others
    0.10
     his
    0.09
     colleagues
    0.08
     Others
    0.07
     crew
    0.07
     coworkers
    0.07
    Others
    0.07
    others
    0.07
     co
    0.06
     suoi
    0.06
    Activations Density 0.017%

    No Known Activations