© 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. 57548
    Prev
    Next
    INDEX
    Explanations

    Movie/TV show plots/scenes

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric tokens containing decimal‐point values (i.e. floating‐point numbers).

    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
     cognitive
    -0.08
    .image
    -0.07
     هنگ
    -0.07
     rip
    -0.07
     Baz
    -0.07
     iron
    -0.07
     fly
    -0.07
     blaze
    -0.06
     canopy
    -0.06
     Cognitive
    -0.06
    POSITIVE LOGITS
     �
    0.06
     обеспе
    0.06
     UIBarButtonItem
    0.06
    NJ
    0.06
    PDOException
    0.06
    _invalid
    0.06
     �
    0.06
     ['$
    0.06
    ="#"
    0.06
     trăm
    0.05
    Activations Density 0.053%

    No Known Activations