© 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. 59139
    Prev
    Next
    INDEX
    Explanations

    scientific research

    np_max-act · gemini-2.0-flash

    The neuron is strongly activated by multi‐character technical terms or abbreviations (often containing digits, uppercase letters, hyphens, or slashes) such as “3D/CAD-CAM,” “cell-free,” and “exosomal-m.”

    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
    uits
    -0.07
     manic
    -0.07
     ocas
    -0.07
    ,A
    -0.07
    ｗｗ
    -0.07
     strán
    -0.06
     subdiv
    -0.06
    ící
    -0.06
    iday
    -0.06
    .steps
    -0.06
    POSITIVE LOGITS
     HT
    0.06
    autop
    0.06
     junit
    0.06
     PropertyInfo
    0.06
     Bison
    0.06
    billing
    0.06
     BorderRadius
    0.06
     JOptionPane
    0.06
     péri
    0.06
     PIT
    0.06
    Activations Density 0.145%

    No Known Activations