© 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. 57817
    Prev
    Next
    INDEX
    Explanations

    references to legal proceedings and investigations involving individuals

    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
    ream
    -0.07
    aste
    -0.07
    anded
    -0.07
    éŁ
    -0.07
     Hlav
    -0.07
    ighb
    -0.06
    urtle
    -0.06
    _inside
    -0.06
    nen
    -0.06
    ey
    -0.06
    POSITIVE LOGITS
     suspect
    0.10
     Sus
    0.08
     wanted
    0.08
     suspects
    0.08
     suspicion
    0.07
     Interest
    0.07
     interest
    0.07
    Interest
    0.07
    ardin
    0.07
     suspicious
    0.07
    Activations Density 0.028%

    No Known Activations