© 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. 107194
    Prev
    Next
    INDEX
    Explanations

    expressions of pride and accomplishment related to clients or organizations

    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
    omik
    -0.08
    omi
    -0.08
    èo
    -0.08
    лаж
    -0.07
    ãģĹãģĭ
    -0.07
    arend
    -0.07
    ÎIJ
    -0.07
    nze
    -0.06
    ÑĥÑģÑĤа
    -0.06
     hatta
    -0.06
    POSITIVE LOGITS
    dit
    0.10
     gain
    0.08
     meanwhile
    0.08
     likewise
    0.07
    ewis
    0.07
     because
    0.07
     benefit
    0.07
    ált
    0.06
     dit
    0.06
    åĪĻ
    0.06
    Activations Density 0.029%

    No Known Activations