© 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. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 17850
    Prev
    Next
    INDEX
    Explanations

    Knowing someone or something

    np_max-act · gemini-2.0-flash

    informal flirtation and playful teasing in conversations.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _even
    -0.06
     NEGLIGENCE
    -0.06
    HOOK
    -0.06
     Vz
    -0.06
    ERIC
    -0.06
     oro
    -0.06
    af
    -0.06
    [f
    -0.05
     eventType
    -0.05
    =key
    -0.05
    POSITIVE LOGITS
     three
    0.07
     rearr
    0.07
     dece
    0.06
    light
    0.06
     gigg
    0.06
     specification
    0.06
     offshore
    0.06
    Checking
    0.06
     dissatisfaction
    0.06
     endregion
    0.06
    Activations Density 0.035%

    No Known Activations