© 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. 30032
    Prev
    Next
    INDEX
    Explanations

    custody

    np_max-act · gemini-2.0-flash

    The neuron activates on terms and phrases related to child custody, visitation, parenting time, and support.

    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
     DEAL
    -0.06
     Chapel
    -0.06
    .bar
    -0.06
    .Mod
    -0.06
    .quest
    -0.06
    inh
    -0.06
     भग
    -0.06
     sns
    -0.06
    alth
    -0.06
    \\
    -0.06
    POSITIVE LOGITS
    ㅠㅠ
    0.07
     später
    0.07
     좌
    0.07
    onestly
    0.07
     La
    0.07
    िस
    0.06
     다음과
    0.06
     друж
    0.06
    -gray
    0.06
     организма
    0.06
    Activations Density 0.004%

    No Known Activations