© 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. 43464
    Prev
    Next
    INDEX
    Explanations

    name

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on the word “name,” especially when it appears in user questions asking for the assistant’s name.

    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
    ive
    -0.07
     Taking
    -0.07
     Giants
    -0.07
     shares
    -0.07
     sik
    -0.06
    лки
    -0.06
    poly
    -0.06
     就
    -0.06
    dk
    -0.06
    Merge
    -0.06
    POSITIVE LOGITS
    .defaultProps
    0.06
    weekly
    0.06
    ulumi
    0.06
    estruct
    0.06
    (IntPtr
    0.06
    (current
    0.06
     unanimous
    0.06
    пня
    0.06
     alumnos
    0.06
     راست
    0.06
    Activations Density 0.013%

    No Known Activations