© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 59195
    Prev
    Next
    INDEX
    Explanations

    Knowledge compilation from various sources

    np_max-act · gemini-2.0-flash

    This neuron responds to relatively rare or domain‐specific content words (e.g. proper names, unusual technical terms, or uncommon nouns).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     two
    -0.06
     area
    -0.06
     IRepository
    -0.06
    Developer
    -0.06
     undergrad
    -0.06
    Sensor
    -0.06
    ");↵↵
    -0.06
     archetype
    -0.06
     appears
    -0.06
     acad
    -0.06
    POSITIVE LOGITS
    fontSize
    0.07
    vailability
    0.07
     DETAILS
    0.07
    sgi
    0.06
    NI
    0.06
     toch
    0.06
     footwear
    0.06
     Pay
    0.06
    EqualityComparer
    0.06
    _OID
    0.06
    Activations Density 0.630%

    No Known Activations