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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 758
    Prev
    Next
    INDEX
    Explanations

    warmth

    np_max-act · gemini-2.0-flash

    This neuron activates on words and phrases that describe a cozy, inviting sense of comfort and warmth in home décor or atmosphere.

    oai_token-act-pair · o4-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
     плат
    -0.07
     충
    -0.06
    Flash
    -0.06
    ardu
    -0.06
     собі
    -0.06
    idebar
    -0.06
    混
    -0.06
    earn
    -0.06
    과
    -0.06
     дуже
    -0.06
    POSITIVE LOGITS
     artic
    0.08
     minim
    0.07
     sunrise
    0.07
     cozy
    0.07
    elif
    0.07
     welcoming
    0.07
     Patriot
    0.07
     CRT
    0.06
     YE
    0.06
     WE
    0.06
    Activations Density 0.013%

    No Known Activations