© 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. 68303
    Prev
    Next
    INDEX
    Explanations

    intelligent

    np_max-act · gemini-2.0-flash

    characters and relationships in romantic and erotic contexts.

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

    The neuron fires on descriptive adjectives denoting a person’s positive traits or qualities.

    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
    MF
    -0.07
    وپ
    -0.06
    Counts
    -0.06
    .Text
    -0.06
     dames
    -0.06
    ทย
    -0.06
    щины
    -0.06
    Opened
    -0.06
     {});↵
    -0.06
    şi
    -0.06
    POSITIVE LOGITS
    igInteger
    0.09
    라도
    0.07
     elo
    0.07
     intelligent
    0.06
     Template
    0.06
     attravers
    0.06
    ={(
    0.06
    eros
    0.06
     самостоятельно
    0.06
    Enh
    0.06
    Activations Density 0.009%

    No Known Activations