© 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. 27870
    Prev
    Next
    INDEX
    Explanations

    geographical/legal restrictions

    np_max-act · gemini-2.0-flash

    legal disclaimers related to financial products and services.

    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
    .getY
    -0.07
     submarines
    -0.07
    ulet
    -0.06
    .startswith
    -0.06
    PIN
    -0.06
    503
    -0.06
     userList
    -0.06
    *width
    -0.06
     Rig
    -0.06
    .Score
    -0.06
    POSITIVE LOGITS
    -round
    0.07
     направ
    0.06
    Jak
    0.06
    .Location
    0.06
    алог
    0.06
     incompet
    0.06
     nastav
    0.06
    (weather
    0.06
    之
    0.06
    θο
    0.06
    Activations Density 0.006%

    No Known Activations