© 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 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. 38887
    Prev
    Next
    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash

    This neuron detects programming identifiers written in all‐caps (e.g. constant names or other code tokens composed entirely of uppercase letters).

    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
    651
    -0.07
    V
    -0.07
    amic
    -0.07
     gelir
    -0.07
     gene
    -0.07
    osc
    -0.07
     Appl
    -0.07
     propName
    -0.07
     carbohydrate
    -0.07
    Roger
    -0.06
    POSITIVE LOGITS
    etooth
    0.07
    _TUN
    0.06
     мови
    0.06
    genden
    0.06
    |unique
    0.06
     Ін
    0.06
     getCurrent
    0.06
    /init
    0.06
    .getSelection
    0.06
     UIAlertView
    0.06
    Activations Density 0.033%

    No Known Activations