© 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. 90620
    Prev
    Next
    INDEX
    Explanations

    Attorney

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of attorneys or legal‐counsel titles (e.g. “Attorney,” “Public Defender,” and related role labels).

    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
    !↵↵↵↵
    -0.07
     Rockefeller
    -0.07
    .scope
    -0.07
    pm
    -0.07
    、、
    -0.06
    ходим
    -0.06
     SHORT
    -0.06
     sollten
    -0.06
    Messages
    -0.06
    .staff
    -0.06
    POSITIVE LOGITS
    ainless
    0.06
    rysler
    0.06
     relentlessly
    0.06
    thern
    0.06
    اية
    0.06
    PCI
    0.06
    .Accessible
    0.06
     NgModule
    0.06
    intosh
    0.06
    -language
    0.06
    Activations Density 0.004%

    No Known Activations