© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 55964
    Prev
    Next
    INDEX
    Explanations

    retirement

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of retirement and related planning‐and‐withdrawal terms.

    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
     Boxing
    -0.07
    uggage
    -0.06
    kea
    -0.06
    ندي
    -0.06
    ('$
    -0.06
    ือ
    -0.06
     Kennedy
    -0.06
     Başkanı
    -0.06
    〔
    -0.06
    форт
    -0.06
    POSITIVE LOGITS
    ้าม
    0.07
     ayak
    0.06
     isActive
    0.06
    roit
    0.06
    (Boolean
    0.06
     landing
    0.06
     SSL
    0.06
    URL
    0.06
    Gradient
    0.06
    Daemon
    0.06
    Activations Density 0.008%

    No Known Activations