© 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
    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. 7602
    Prev
    Next
    INDEX
    Explanations

    movies

    np_max-act · gemini-2.0-flash

    This neuron primarily detects mentions of the film title “Metropolis.”

    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
     کودکان
    -0.07
     immediate
    -0.06
    得
    -0.06
     className
    -0.06
     AdapterView
    -0.06
    左右
    -0.06
    /gin
    -0.06
     Booker
    -0.06
    Behind
    -0.06
     Bookmark
    -0.06
    POSITIVE LOGITS
     pumped
    0.06
    _DRV
    0.06
    *dx
    0.06
     Üst
    0.06
    bulk
    0.06
     STAT
    0.06
     силь
    0.06
    FTP
    0.06
     blasph
    0.06
     hn
    0.06
    Activations Density 0.011%

    No Known Activations