© 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. 128057
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude and personal reflections on health struggles

    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
     vind
    -0.07
     rem
    -0.06
     hast
    -0.06
    spir
    -0.06
     synthetic
    -0.06
     former
    -0.06
    Enlarge
    -0.06
    unca
    -0.06
    uess
    -0.06
    inan
    -0.06
    POSITIVE LOGITS
    ÐĿÐĺ
    0.07
    )null
    0.06
    éri
    0.06
    ÐĶÐļ
    0.06
    .findByIdAndUpdate
    0.06
    zew
    0.06
    éra
    0.06
    eron
    0.06
    å¹¹ç·ļ
    0.06
    rios
    0.06
    Activations Density 0.013%

    No Known Activations