© 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. 77668
    Prev
    Next
    INDEX
    Explanations

    references to security breaches and related criminal activities

    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
    å¼¥
    -0.07
    enza
    -0.07
    anca
    -0.07
    à¹Īร
    -0.06
    ãĤ¥
    -0.06
     Pence
    -0.06
    stva
    -0.06
    ctp
    -0.06
    553
    -0.06
    лÑĭ
    -0.06
    POSITIVE LOGITS
     recent
    0.14
     lately
    0.14
     recently
    0.13
    recent
    0.12
     Recent
    0.11
     Recently
    0.10
    Recent
    0.10
    Recently
    0.10
    _recent
    0.10
    æľĢè¿ij
    0.09
    Activations Density 0.040%

    No Known Activations