© 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. 58871
    Prev
    Next
    INDEX
    Explanations

    stop words

    np_max-act · gemini-2.0-flash

    The neuron is triggered by sentence-initial transition or discourse words (e.g. “The,” “This,” “But,” “It”) marking the start of a new statement.

    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
    getter
    -0.06
     K
    -0.06
     mount
    -0.06
     discussed
    -0.06
    quin
    -0.06
     QMessageBox
    -0.06
     award
    -0.06
    _plan
    -0.06
     k
    -0.06
    _PRED
    -0.06
    POSITIVE LOGITS
     naï
    0.06
     době
    0.06
     haute
    0.06
    AxisSize
    0.06
     тран
    0.06
     nao
    0.06
    .Validation
    0.06
    ¥
    0.06
     hardships
    0.06
     Batt
    0.06
    Activations Density 0.030%

    No Known Activations