© 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. 109135
    Prev
    Next
    INDEX
    Explanations

    Beans

    np_max-act · gemini-2.0-flash

    terms related to software licensing and legal agreements.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron fires on mentions of “NetBeans,” spotting occurrences of the IDE’s name in text.

    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
     alignment
    -0.07
     filt
    -0.07
     dysfunction
    -0.06
     terminator
    -0.06
    音樂
    -0.06
     вла
    -0.06
     scoring
    -0.06
    semble
    -0.06
     Jian
    -0.06
     �
    -0.06
    POSITIVE LOGITS
    -LAST
    0.08
    .netbeans
    0.07
     clr
    0.07
    brig
    0.07
     viewHolder
    0.06
    WXYZ
    0.06
    :before
    0.06
     pcb
    0.06
     неб
    0.06
     brutal
    0.06
    Activations Density 0.001%

    No Known Activations