© 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 EvalsExportsinterp-engineNEWAPI 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. 5433
    Prev
    Next
    INDEX
    Explanations

    phrases that express gratitude or recognize dependence on others

    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
    аÑĤки
    -0.08
    antan
    -0.07
    yk
    -0.07
     zwar
    -0.07
    ÃľR
    -0.06
    berger
    -0.06
    ož
    -0.06
    hiba
    -0.06
    holm
    -0.06
    KT
    -0.06
    POSITIVE LOGITS
     contribution
    0.07
    unn
    0.06
    lege
    0.06
    853
    0.06
    گاÙĨ
    0.06
    обÑĢаз
    0.06
     NOR
    0.06
     firstly
    0.06
     nor
    0.06
     contributions
    0.06
    Activations Density 0.007%

    No Known Activations