© 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. 7519
    Prev
    Next
    INDEX
    Explanations

    >

    np_max-act · gemini-2.0-flash

    The neuron fires on decimal version‐style numbers (e.g. “2.626953125” in XML tag values).

    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
    sworth
    -0.07
     Blanch
    -0.06
     pineapple
    -0.06
    殊
    -0.06
     Angeles
    -0.06
     Chí
    -0.06
     прин
    -0.06
     hardness
    -0.06
    ิค
    -0.06
     rupture
    -0.06
    POSITIVE LOGITS
    -<?
    0.07
    iod
    0.07
    ov
    0.07
    ,v
    0.07
    km
    0.07
    ">{{
    0.07
    >j
    0.07
    =d
    0.07
    "><?
    0.07
    curr
    0.07
    Activations Density 0.014%

    No Known Activations