© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 13506
    Prev
    Next
    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash

    The neuron activates on angle-bracketed type parameters (e.g. “<String>”) in generic declarations.

    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
     subtype
    -0.07
    UFFIX
    -0.07
    az
    -0.06
    widget
    -0.06
    XPath
    -0.06
     annot
    -0.06
    งข
    -0.06
    wit
    -0.06
    993
    -0.06
    oop
    -0.06
    POSITIVE LOGITS
     проблем
    0.08
    <String
    0.07
    <Tag
    0.07
     NSDate
    0.07
     Nissan
    0.06
     upfront
    0.06
     @{$
    0.06
     青
    0.06
     Mn
    0.06
     побед
    0.06
    Activations Density 0.015%

    No Known Activations