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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RESID-POST-AA
    11. 57831
    Prev
    Next
    INDEX
    Explanations

    Errors

    np_max-act · gemini-2.0-flash

    This neuron fires on code identifiers and tokens related to validation rule violations (e.g. “RuleViolation”, collections of violations, and related error‐reporting methods).

    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
    ETF
    -0.06
    INPUT
    -0.06
     HH
    -0.06
     Society
    -0.06
     '&
    -0.06
    宏
    -0.06
     aluno
    -0.06
    CompatActivity
    -0.06
     angles
    -0.06
     mẫu
    -0.06
    POSITIVE LOGITS
     chronological
    0.06
     deserving
    0.06
    elerik
    0.06
     newcom
    0.06
    SAN
    0.06
     olmaz
    0.06
    .man
    0.05
    رى
    0.05
     Vader
    0.05
    ULT
    0.05
    Activations Density 0.011%

    No Known Activations