© 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. 15-LLAMASCOPE-RES-131K
    11. 87407
    Prev
    Next
    INDEX
    Explanations

    words and phrases that convey beauty, emotion, or positive outcomes

    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
     either
    -0.08
    EDI
    -0.06
    laz
    -0.06
    eh
    -0.06
    keh
    -0.06
    ÅĦst
    -0.06
     Academ
    -0.06
    yal
    -0.06
    ếp
    -0.06
    _SER
    -0.06
    POSITIVE LOGITS
     etc
    0.16
     and
    0.13
    etc
    0.11
    çŃī
    0.10
    ãģĿãģĹãģ¦
    0.10
    /etc
    0.10
     alike
    0.09
     vÃł
    0.09
     и
    0.09
     &
    0.08
    Activations Density 0.089%

    No Known Activations