© 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. 89579
    Prev
    Next
    INDEX
    Explanations

    Data processing

    np_max-act · gemini-2.0-flash

    This neuron fires on tokens that refer to reading or consuming data from buffers or queues (e.g. “read,” “consumer,” “consumers”).

    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
     texting
    -0.06
    =X
    -0.06
     lui
    -0.06
    ologists
    -0.06
    tures
    -0.06
     Wade
    -0.06
    reat
    -0.06
     Liu
    -0.06
     Jeh
    -0.06
     caller
    -0.06
    POSITIVE LOGITS
     현재
    0.08
    _unused
    0.07
    ун
    0.07
     various
    0.07
     sebuah
    0.06
    Similarly
    0.06
     SCN
    0.06
     Perform
    0.06
    ypress
    0.06
    一般
    0.06
    Activations Density 0.152%

    No Known Activations