© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 94439
    Prev
    Next
    INDEX
    Explanations

    emotional expressions related to familial relationships

    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
     Fee
    -0.07
     //$
    -0.06
    OrFail
    -0.06
    ologne
    -0.06
    uai
    -0.06
    datatable
    -0.06
    ÃľM
    -0.06
     stepping
    -0.06
     duty
    -0.06
    ÑĥÑī
    -0.06
    POSITIVE LOGITS
     Cust
    0.07
     RHS
    0.06
    cust
    0.06
     cust
    0.06
    GLfloat
    0.06
    éŁ¿
    0.06
    arks
    0.06
    VICES
    0.06
    /signup
    0.06
    SWEP
    0.06
    Activations Density 0.019%

    No Known Activations