© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 40977
    Prev
    Next
    INDEX
    Explanations

    terms related to sensitivity and sensitive conditions or topics

    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
    dden
    -0.09
    illard
    -0.08
    anh
    -0.08
    oded
    -0.08
    atee
    -0.07
     Äijại
    -0.07
    _BAND
    -0.07
    imizer
    -0.07
    amate
    -0.07
    ongan
    -0.07
    POSITIVE LOGITS
     sensitive
    0.09
    -sensitive
    0.09
     sensitivity
    0.08
    Sensitive
    0.07
     toward
    0.06
    ensitive
    0.06
     regard
    0.06
     touch
    0.06
     sens
    0.06
    ires
    0.06
    Activations Density 0.013%

    No Known Activations