© 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. 81417
    Prev
    Next
    INDEX
    Explanations

    expressions of emotional reactions or feelings

    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
    stu
    -0.07
    agate
    -0.07
     VÅ¡ech
    -0.07
    jd
    -0.07
    andalone
    -0.07
    amaha
    -0.07
    oplayer
    -0.07
     reck
    -0.07
    åĽ°
    -0.07
    osomal
    -0.06
    POSITIVE LOGITS
    ikal
    0.07
     Millenn
    0.06
    ¦¬
    0.06
     ØŃزب
    0.06
    zym
    0.06
     guys
    0.06
     zad
    0.06
    elo
    0.06
    .googlecode
    0.06
     tips
    0.06
    Activations Density 0.014%

    No Known Activations