© 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. 71237
    Prev
    Next
    INDEX
    Explanations

    terms related to legal consequences and penalties

    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
    ulfilled
    -0.08
    isd
    -0.07
    Å¡ÃŃ
    -0.07
    adiens
    -0.07
    LC
    -0.07
    _fake
    -0.07
    agner
    -0.07
     dÃŃ
    -0.06
    سÙĪب
    -0.06
     merak
    -0.06
    POSITIVE LOGITS
     stigma
    0.09
     Clearance
    0.07
     employment
    0.06
    ãģ¥
    0.06
    953
    0.06
    Pager
    0.06
     social
    0.06
    夢
    0.06
    Resume
    0.06
     clearance
    0.06
    Activations Density 0.006%

    No Known Activations