© 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. 59083
    Prev
    Next
    INDEX
    Explanations

    Importance

    np_max-act · gemini-2.0-flash

    This neuron detects evaluative words or phrases that signal importance or (ir)relevance, such as “important,” “irrelevant,” “matter,” or “nicht wichtig.”

    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
     Bolshevik
    -0.07
    937
    -0.07
    Books
    -0.06
    ึกษ
    -0.06
    里
    -0.06
     PCM
    -0.06
     со
    -0.06
     služ
    -0.06
    TEMPLATE
    -0.06
     fleece
    -0.06
    POSITIVE LOGITS
     бюджет
    0.07
     urg
    0.07
    .series
    0.07
     belang
    0.07
    (real
    0.06
     Buddhist
    0.06
    _ut
    0.06
    езд
    0.06
    üph
    0.06
    (det
    0.06
    Activations Density 0.023%

    No Known Activations