© 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. 13467
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    The neuron fires most strongly on programming‐style punctuation (braces, parentheses, semicolons, etc.) indicating code syntax.

    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
    dialog
    -0.06
     extortion
    -0.06
     QMap
    -0.06
    ึกษ
    -0.06
    kem
    -0.06
     Fairfax
    -0.06
     CPL
    -0.06
    "];
↵
    -0.06
    :///
    -0.06
     crossword
    -0.06
    POSITIVE LOGITS
     complete
    0.07
    魔
    0.06
     LIGHT
    0.06
    .Make
    0.06
    	T
    0.06
     Una
    0.06
    ‌رس
    0.06
     существует
    0.06
    اورزی
    0.06
     możli
    0.06
    Activations Density 0.014%

    No Known Activations