© 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. 55545
    Prev
    Next
    INDEX
    Explanations

    CC

    np_max-act · gemini-2.0-flash

    The neuron fires on code identifiers—especially uppercase or CamelCase names (e.g. macros, class/struct names, constants) in code snippets.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    programming/code tokens such as function/class/constant names and other identifier-like strings (CamelCase, ALL_CAPS, API names).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
     Completely
    -0.06
     narrator
    -0.06
     sentir
    -0.06
     Islam
    -0.06
     Plaza
    -0.06
     bak
    -0.06
     عشر
    -0.06
     chiar
    -0.06
     Král
    -0.06
     Girl
    -0.06
    POSITIVE LOGITS
    –
    0.08
    :A
    0.07
    A
    0.07
    ポ
    0.07
    _ANS
    0.07
    �
    0.07
    �
    0.06
    ++)
↵
    0.06
    .A
    0.06
    bfd
    0.06
    Activations Density 0.715%

    No Known Activations