© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 59049
    Prev
    Next
    INDEX
    Explanations

    '{'

    np_max-act · gemini-2.0-flash

    The neuron is triggered by sequences of digits and dots—that is, it detects IP addresses in the 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
     outside
    -0.06
    CLOSE
    -0.06
    Marc
    -0.06
    ANE
    -0.06
    ########################################################
    -0.06
    ERİ
    -0.06
    iliation
    -0.05
    RU
    -0.05
    elson
    -0.05
     Dawson
    -0.05
    POSITIVE LOGITS
     sona
    0.08
     hton
    0.07
    .writeFileSync
    0.07
    .timeScale
    0.07
    .SetFloat
    0.07
     Settings
    0.07
    vably
    0.07
     wood
    0.06
    .setStyle
    0.06
     render
    0.06
    Activations Density 0.002%

    No Known Activations