© 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. 89043
    Prev
    Next
    INDEX
    Explanations

    .java

    np_max-act · gemini-2.0-flash

    This neuron fires on the file‐and‐line references you see in Java stack traces (e.g. “ClassName.java:123”).

    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
     mujer
    -0.06
    License
    -0.06
     cry
    -0.06
    Jones
    -0.06
     Immigration
    -0.06
    ịa
    -0.06
     Burl
    -0.06
     vše
    -0.06
    摸
    -0.06
     rsp
    -0.06
    POSITIVE LOGITS
    	parser
    0.07
     envision
    0.07
    ὰ
    0.06
     decorations
    0.06
     '>
    0.06
     раза
    0.06
     gấp
    0.06
    Accepted
    0.06
     feasible
    0.06
     timestamp
    0.06
    Activations Density 0.004%

    No Known Activations