© 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 EvalsExportsAPI 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. 56525
    Prev
    Next
    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash

    This neuron primarily activates on punctuation and structural markers (periods and step breaks), effectively identifying sentence or step boundaries.

    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
    _iteration
    -0.06
    indicator
    -0.06
    รรม
    -0.06
    éal
    -0.06
    cı
    -0.06
    ony
    -0.06
     عش
    -0.06
     Instructor
    -0.06
    ียญ
    -0.06
    汽车
    -0.06
    POSITIVE LOGITS
     partial
    0.07
    .Enable
    0.06
     providedIn
    0.06
    .Location
    0.06
     سطح
    0.06
     тоб
    0.06
     Quyết
    0.06
    άρ
    0.06
     Дон
    0.06
     vale
    0.06
    Activations Density 0.080%

    No Known Activations