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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 7955
    Prev
    Next
    INDEX
    Explanations

    }

    np_max-act · gemini-2.0-flash

    The neuron fires on the opening of code blocks (i.e. the “{” tokens that begin class/method bodies).

    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
    妮
    -0.08
    -house
    -0.07
     anomal
    -0.07
     prisoner
    -0.07
     (('
    -0.07
    okrat
    -0.07
     centr
    -0.06
    on
    -0.06
    еч
    -0.06
     Circ
    -0.06
    POSITIVE LOGITS
     раст
    0.07
    Vec
    0.06
     всем
    0.06
    Invoice
    0.06
    Dec
    0.06
     değil
    0.06
    :NSLocalizedString
    0.06
    ної
    0.06
     выпол
    0.06
    /up
    0.06
    Activations Density 0.014%

    No Known Activations