© 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 EvalsExportsinterp-engineNEWAPI 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. 62354
    Prev
    Next
    INDEX
    Explanations

    phrases expressing strong emotional sentiments

    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
    que
    -0.07
     Spicer
    -0.06
    adder
    -0.06
    ocracy
    -0.05
    elf
    -0.05
    linkplain
    -0.05
    ning
    -0.05
    æĮģ
    -0.05
    ocity
    -0.05
    v
    -0.05
    POSITIVE LOGITS
    .exc
    0.07
    ledon
    0.07
    ¥IJ
    0.07
    Fmt
    0.07
    вин
    0.07
     Ñįлек
    0.07
     Doll
    0.06
    empo
    0.06
    ebek
    0.06
    änder
    0.06
    Activations Density 0.012%

    No Known Activations