© 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. 105419
    Prev
    Next
    INDEX
    Explanations

    instances of emotional expressions or reactions

    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
     integr
    -0.06
    824
    -0.06
    esi
    -0.06
    CCC
    -0.06
    Delegate
    -0.06
     intens
    -0.05
     Luck
    -0.05
    YL
    -0.05
     Integr
    -0.05
    æŃ£
    -0.05
    POSITIVE LOGITS
    kla
    0.08
    ignum
    0.07
    least
    0.07
    chg
    0.07
    kaar
    0.07
    opa
    0.06
    oku
    0.06
    <source
    0.06
    enga
    0.06
    tgl
    0.06
    Activations Density 0.025%

    No Known Activations