Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 85322
    Prev
    Next
    INDEX
    Explanations

    Blog posts/chat logs

    np_max-act · gemini-2.0-flash

    The neuron fires on plainspoken self-descriptions of being “just a straight-up likable person.”

    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
    	friend
    -0.07
     Inhal
    -0.07
     wom
    -0.07
     favicon
    -0.07
    Prop
    -0.07
    нив
    -0.06
     ice
    -0.06
     verd
    -0.06
    ")]↵↵
    -0.06
    _portal
    -0.06
    POSITIVE LOGITS
    起来
    0.07
    ół
    0.06
    ées
    0.06
     Assumes
    0.06
     szy
    0.06
    और
    0.06
     kolej
    0.06
    gars
    0.06
    012
    0.06
     différents
    0.06
    Activations Density 0.001%

    No Known Activations