© 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. 80202
    Prev
    Next
    INDEX
    Explanations

    was

    np_max-act · gemini-2.0-flash

    scientific names and classifications of species.

    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
     assurances
    -0.07
    FUN
    -0.06
     baskı
    -0.06
    reating
    -0.06
    \views
    -0.06
     Před
    -0.06
    ência
    -0.06
    ologies
    -0.06
    .TEXT
    -0.06
    inions
    -0.06
    POSITIVE LOGITS
    900
    0.07
    燃
    0.07
    condition
    0.06
     Stars
    0.06
     освіт
    0.06
    τια
    0.06
     writes
    0.06
     aşam
    0.06
    ;color
    0.06
    WithType
    0.06
    Activations Density 0.007%

    No Known Activations