© 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. 9491
    Prev
    Next
    INDEX
    Explanations

    personal experiences

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on phrases that refer to an exclusive pair—especially “the two of us” or “just us two.”

    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
    něž
    -0.07
     slashes
    -0.06
    umber
    -0.06
     IPC
    -0.06
     Có
    -0.06
     cp
    -0.06
     Ở
    -0.06
    이야
    -0.06
    managed
    -0.06
    mint
    -0.06
    POSITIVE LOGITS
    .Relative
    0.07
    :'+
    0.06
     ():
    0.06
     teach
    0.06
     içerisinde
    0.06
    發
    0.06
    ishing
    0.06
    jas
    0.06
    sey
    0.06
    uta
    0.06
    Activations Density 0.009%

    No Known Activations