© 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. 92101
    Prev
    Next
    INDEX
    Explanations

    would

    np_max-act · gemini-2.0-flash

    references to ongoing legal matters and settlements.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron fires on expressions of personal stance or recommendation, especially the phrase “I would.”

    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
    _slow
    -0.07
    05
    -0.07
    03
    -0.06
    _Timer
    -0.06
    Ra
    -0.06
    _scr
    -0.06
    jumbotron
    -0.06
    _quotes
    -0.06
    .getSource
    -0.06
    Basket
    -0.06
    POSITIVE LOGITS
    Based
    0.08
     قدرت
    0.08
     ولك
    0.07
    depend
    0.07
     embod
    0.06
     رج
    0.06
     đích
    0.06
     setObject
    0.06
     imb
    0.06
     Burk
    0.06
    Activations Density 0.023%

    No Known Activations