© 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 EvalsExportsAPI 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. 85753
    Prev
    Next
    INDEX
    Explanations

    emotional responses related to health and family issues

    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
    rens
    -0.07
    /Instruction
    -0.07
    linky
    -0.07
     âĹĦ
    -0.07
    ''"
    -0.07
    ucht
    -0.07
    engin
    -0.06
    /ay
    -0.06
    alars
    -0.06
    @student
    -0.06
    POSITIVE LOGITS
     immediately
    0.07
     Consultants
    0.07
     instantly
    0.06
    972
    0.06
     shock
    0.06
     initially
    0.06
     emotions
    0.06
     emotion
    0.06
    oya
    0.06
     families
    0.06
    Activations Density 0.006%

    No Known Activations