© 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. 38367
    Prev
    Next
    INDEX
    Explanations

    probability problems

    np_max-act · gemini-2.0-flash

    The neuron fires on floating‐point probability values (decimal numbers like “2.6875,” “3.21289,” etc.).

    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
     ethnic
    -0.06
     Gra
    -0.06
    quests
    -0.06
    .article
    -0.06
    /course
    -0.06
    洛
    -0.06
    coeff
    -0.06
    001
    -0.06
     Completed
    -0.06
    (red
    -0.06
    POSITIVE LOGITS
     Marathon
    0.07
     drawback
    0.06
     drawbacks
    0.06
    inte
    0.06
     Xm
    0.06
    "]:
    0.06
     Stephanie
    0.06
    	counter
    0.06
     Hitler
    0.06
    ΕΥ
    0.06
    Activations Density 0.000%

    No Known Activations