© 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. 7907
    Prev
    Next
    INDEX
    Explanations

    inspections

    np_max-act · gemini-2.0-flash

    The neuron is triggered by mentions of formal regulatory oversight actions—inspections, audits, examinations, and compliance checks.

    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
     Lan
    -0.07
     dedicate
    -0.06
    em
    -0.06
    eb
    -0.06
    发布
    -0.06
     li
    -0.06
    807
    -0.06
    ائل
    -0.05
    OP
    -0.05
     Libyan
    -0.05
    POSITIVE LOGITS
    .ts
    0.07
    학년도
    0.07
     bras
    0.07
    conditional
    0.07
     ^{↵
    0.06
     Vibr
    0.06
    snapshot
    0.06
     truly
    0.06
     bots
    0.06
     bree
    0.06
    Activations Density 0.014%

    No Known Activations