© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 124664
    Prev
    Next
    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash

    This neuron fires on snippets of programming code—especially capitalized language keywords (e.g. SQL or C++/PHP/Java keywords) and code-style tokens.

    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
    (gray
    -0.07
     lé
    -0.07
    Mag
    -0.07
     COMMENTS
    -0.07
    ervations
    -0.06
     ################################################
    -0.06
     яй
    -0.06
    ufen
    -0.06
    _utilities
    -0.06
    ائر
    -0.06
    POSITIVE LOGITS
     `.
    0.06
    Remaining
    0.06
     MCU
    0.06
    通知
    0.06
    .$.
    0.06
    km
    0.06
    HeaderView
    0.06
     flyers
    0.06
    ')[
    0.05
    Fx
    0.05
    Activations Density 0.146%

    No Known Activations