© 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. 60591
    Prev
    Next
    INDEX
    Explanations

    punctuations and patterns of encouragement or emotional support

    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
    ediator
    -0.07
     ours
    -0.07
     our
    -0.07
    ourd
    -0.07
     OUR
    -0.06
     theirs
    -0.06
    dae
    -0.06
    zego
    -0.06
    iydi
    -0.06
    REQ
    -0.06
    POSITIVE LOGITS
     yourself
    0.09
    ickt
    0.07
    idden
    0.06
    945
    0.06
     GLint
    0.06
     refuse
    0.06
    ãģ¨ãģĵãĤį
    0.06
     Teknik
    0.06
    deen
    0.06
     redistrib
    0.06
    Activations Density 0.001%

    No Known Activations