Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 41757
    Prev
    Next
    INDEX
    Explanations

    Zone

    np_max-act · gemini-2.0-flash

    This neuron fires on Objective-C method signatures involving “WithZone” (e.g. allocWithZone:, copyWithZone:).

    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
     imperial
    -0.07
     TAX
    -0.06
    _MM
    -0.06
     بر
    -0.06
     shar
    -0.06
    .Timestamp
    -0.06
    enas
    -0.06
     traff
    -0.06
    	entity
    -0.06
    Say
    -0.06
    POSITIVE LOGITS
     jPanel
    0.07
     isnt
    0.06
    Kernel
    0.06
     CGContext
    0.06
    .spotify
    0.06
    irling
    0.06
     $_[
    0.06
    rych
    0.06
    .readFileSync
    0.06
     Prize
    0.06
    Activations Density 0.002%

    No Known Activations