© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 124564
    Prev
    Next
    INDEX
    Explanations

    exception to a rule

    np_max-act · gemini-2.0-flash

    content related to critical assessments and economic evaluations of assets, particularly in financial contexts.

    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
     tents
    -0.07
    ضی
    -0.07
     lực
    -0.06
    074
    -0.06
     participating
    -0.06
    Lock
    -0.06
     Biom
    -0.06
     ery
    -0.06
    evším
    -0.06
     Lot
    -0.06
    POSITIVE LOGITS
    mond
    0.07
     مشک
    0.07
    Difference
    0.06
     fabs
    0.06
    eddar
    0.06
     MSG
    0.06
    ()};↵
    0.06
     ﾄ
    0.06
    .Produ
    0.06
    ilecek
    0.06
    Activations Density 0.004%

    No Known Activations