© 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. 58892
    Prev
    Next
    INDEX
    Explanations

    negative descriptors and sentiments or issues related to challenges and consequences

    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
     recent
    -0.08
     Recent
    -0.08
    recent
    -0.08
     presently
    -0.07
    ystate
    -0.07
     currently
    -0.07
    ÑĢеÑĪ
    -0.07
    currently
    -0.07
    longleftrightarrow
    -0.07
    ýv
    -0.07
    POSITIVE LOGITS
     minor
    0.06
     smugg
    0.06
     strict
    0.06
     ab
    0.06
    246
    0.06
    rag
    0.06
     Heavenly
    0.05
     lived
    0.05
    à¥įत
    0.05
    f
    0.05
    Activations Density 0.004%

    No Known Activations