© 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. 128793
    Prev
    Next
    INDEX
    Explanations

    Android app development code

    np_max-act · gemini-2.0-flash

    This neuron activates on programming code tokens, especially Java syntax elements like method calls, identifiers, and punctuation.

    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
    Vol
    -0.07
    Allocator
    -0.07
    .contacts
    -0.06
    imp
    -0.06
    contacts
    -0.06
    .active
    -0.06
    ياه
    -0.06
    OUNTER
    -0.06
     colore
    -0.06
    .STRING
    -0.06
    POSITIVE LOGITS
    uluk
    0.06
     وصل
    0.06
     Incorpor
    0.06
    Salir
    0.06
     yytype
    0.06
    da
    0.05
     Ο
    0.05
     Update
    0.05
    "),
    ↵
    0.05
     Μα
    0.05
    Activations Density 0.022%

    No Known Activations