© 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. 27766
    Prev
    Next
    INDEX
    Explanations

    personal experiences

    np_max-act · gemini-2.0-flash

    toxic expressions and negative sentiments in personal relationships.

    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
    (nodes
    -0.06
    _profile
    -0.06
    .rooms
    -0.06
     mosquitoes
    -0.06
    (search
    -0.06
     khỏ
    -0.06
    diler
    -0.06
     conscious
    -0.06
    _upd
    -0.06
    .Text
    -0.06
    POSITIVE LOGITS
    šla
    0.07
    ierte
    0.07
    �
    0.07
     ostrov
    0.07
    erta
    0.07
     paar
    0.07
    êm
    0.06
     Thế
    0.06
    	Block
    0.06
    iena
    0.06
    Activations Density 0.028%

    No Known Activations