© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 119306
    Prev
    Next
    INDEX
    Explanations

    references to interpersonal relationships and community interactions

    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
    uil
    -0.06
    mong
    -0.06
    oph
    -0.06
    окон
    -0.06
     Guil
    -0.06
     Opp
    -0.06
    ÚĺÙĩ
    -0.06
     chilled
    -0.06
    Ws
    -0.06
    ermal
    -0.06
    POSITIVE LOGITS
    ovaly
    0.08
     detox
    0.07
    /Foundation
    0.07
     NodeList
    0.07
    -module
    0.07
     intake
    0.07
    å¤Ħ
    0.07
    çħ
    0.07
    оÑĢÑĸ
    0.07
    quential
    0.06
    Activations Density 0.001%

    No Known Activations