© 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. 125748
    Prev
    Next
    INDEX
    Explanations

    terms related to legal concepts of immunity and liability

    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
    gregator
    -0.07
    opensource
    -0.07
     Underground
    -0.07
    criptor
    -0.07
    affer
    -0.07
    اÙĨÙĩ
    -0.06
    linger
    -0.06
     Ñĥмов
    -0.06
    ASM
    -0.06
    astle
    -0.06
    POSITIVE LOGITS
     immunity
    0.09
     foreign
    0.07
    à¸Ńà¸Ķ
    0.07
     Sovere
    0.07
     immune
    0.06
     overlap
    0.06
     defenses
    0.06
     Foreign
    0.06
     ex
    0.06
     diplom
    0.06
    Activations Density 0.010%

    No Known Activations