© 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. 28047
    Prev
    Next
    INDEX
    Explanations

    antidepressants

    np_max-act · gemini-2.0-flash

    information about medications used to treat anxiety.

    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
    .ReadFile
    -0.07
    Amb
    -0.06
     vznik
    -0.06
    James
    -0.06
    _names
    -0.06
     Denis
    -0.06
     Аль
    -0.06
     panc
    -0.06
    .Shapes
    -0.06
    分钟
    -0.06
    POSITIVE LOGITS
    oxetine
    0.09
     Cialis
    0.07
     poking
    0.07
     Spreadsheet
    0.06
     suffice
    0.06
     lifted
    0.06
     Erotische
    0.06
    .lr
    0.06
    Titles
    0.06
     cups
    0.06
    Activations Density 0.004%

    No Known Activations