© 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. 45378
    Prev
    Next
    INDEX
    Explanations

    Convergence/repeated calculation

    np_max-act · gemini-2.0-flash

    pseudocode related to the K-Means clustering algorithm.

    oai_token-act-pair · gpt-4o-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
     reputation
    -0.07
     войны
    -0.07
     �
    -0.06
     TEMPLATE
    -0.06
     prefer
    -0.06
    вою
    -0.06
     PARTY
    -0.06
     comprend
    -0.06
     sis
    -0.06
    álu
    -0.06
    POSITIVE LOGITS
     tủ
    0.07
    acades
    0.07
    .jobs
    0.06
    duct
    0.06
     pornos
    0.06
     Synopsis
    0.06
    _left
    0.06
     iff
    0.06
    \Migration
    0.06
    lij
    0.06
    Activations Density 0.027%

    No Known Activations