© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 55933
    Prev
    Next
    INDEX
    Explanations

    workplaces, institutions

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of someone’s job or workplace context (e.g., employment roles and office settings).

    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
     sharp
    -0.07
    .GetName
    -0.07
     parliamentary
    -0.07
    ASHINGTON
    -0.07
    ellant
    -0.06
    _atomic
    -0.06
     resolver
    -0.06
     refusing
    -0.06
    _NUMBER
    -0.06
    (Render
    -0.06
    POSITIVE LOGITS
     ομάδα
    0.06
     полож
    0.06
     iy
    0.06
    ์ส
    0.06
     viết
    0.06
     immature
    0.06
    itech
    0.06
    -global
    0.05
    μοί
    0.05
    �
    0.05
    Activations Density 0.036%

    No Known Activations