© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 126121
    Prev
    Next
    INDEX
    Explanations

    approve

    np_max-act · gemini-2.0-flash

    This neuron detects legal procedural terms referring to court filings and case actions (e.g., account, approval, petition).

    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
     weapon
    -0.07
    .created
    -0.06
    D
    -0.06
     remake
    -0.06
    '>"+
    -0.06
    .MM
    -0.06
    -regexp
    -0.06
     paper
    -0.06
    _route
    -0.06
    _prefix
    -0.06
    POSITIVE LOGITS
    вропей
    0.06
     хорош
    0.06
    “我
    0.06
    (adapter
    0.06
    새
    0.06
    ляет
    0.06
    (clazz
    0.06
     گر
    0.06
     extravag
    0.06
     तब
    0.06
    Activations Density 0.005%

    No Known Activations