© 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. 58951
    Prev
    Next
    INDEX
    Explanations

    _train

    np_max-act · gemini-2.0-flash

    This neuron is essentially inactive (it never activates on any tokens), so it isn’t detecting any pattern.

    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
    _web
    -0.06
    Relations
    -0.06
     rtrim
    -0.06
     Bieber
    -0.06
     Colleg
    -0.06
    ל
    -0.06
     mãe
    -0.06
    Solo
    -0.06
     pickup
    -0.06
     inappropriate
    -0.06
    POSITIVE LOGITS
     flawed
    0.07
    TRL
    0.07
    体系
    0.06
    /${
    0.06
    /man
    0.06
    dbName
    0.06
     Span
    0.06
    TextWriter
    0.06
     struk
    0.06
     seemed
    0.06
    Activations Density 0.002%

    No Known Activations