© 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. 129722
    Prev
    Next
    INDEX
    Explanations

    stdint

    np_max-act · gemini-2.0-flash

    The neuron is triggered by the appearance of the token “stdint” (e.g. in `#include <stdint.h>`).

    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
     müssen
    -0.06
     malloc
    -0.06
     систем
    -0.06
     habit
    -0.06
    |max
    -0.06
     objection
    -0.06
    MULT
    -0.06
     etiqu
    -0.06
    izable
    -0.06
    DESC
    -0.05
    POSITIVE LOGITS
    stdint
    0.11
     declares
    0.08
    _MANAGER
    0.07
    ayım
    0.07
    /business
    0.07
    aired
    0.07
    ovala
    0.06
     Soda
    0.06
    ohan
    0.06
     Jazeera
    0.06
    Activations Density 0.000%

    No Known Activations