© 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
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 36896
    Prev
    Next
    INDEX
    Explanations

    begin

    np_max-act · gemini-2.0-flash

    The neuron detects programming/code content—particularly structural keywords and block/declaration constructs in code.

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     slap
    -0.07
    stem
    -0.07
     niet
    -0.06
    グル
    -0.06
    νας
    -0.06
     soaked
    -0.06
     projectile
    -0.06
    vtk
    -0.06
     dashboard
    -0.06
     GROUP
    -0.06
    POSITIVE LOGITS
    .getPage
    0.07
    ==$
    0.07
    quantity
    0.07
    002
    0.06
     zásob
    0.06
    _Request
    0.06
     سپتامبر
    0.06
    Converter
    0.06
    사무
    0.06
    ฤษภาคม
    0.06
    Activations Density 0.004%

    No Known Activations