© 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. 129757
    Prev
    Next
    INDEX
    Explanations

    .main

    np_max-act · gemini-2.0-flash

    This neuron fires on tokens that occur in Java exception stack traces (e.g. method names, thread identifiers like “main,” class/file references, and line-number contexts).

    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
     wallet
    -0.07
    hit
    -0.07
     worm
    -0.07
     그런
    -0.06
    _done
    -0.06
     Twin
    -0.06
    (tolua
    -0.06
     idiot
    -0.06
    WIN
    -0.06
    	class
    -0.06
    POSITIVE LOGITS
     categorical
    0.06
    783
    0.06
    abor
    0.06
     پیچ
    0.06
    ervations
    0.06
     coppia
    0.06
    로그
    0.06
    -pro
    0.06
    岗位
    0.06
    /car
    0.05
    Activations Density 0.001%

    No Known Activations