© 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. 51273
    Prev
    Next
    INDEX
    Explanations

    question and answer

    np_max-act · gemini-2.0-flash

    content related to mental health and the effects of medication.

    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
    ød
    -0.07
    iance
    -0.07
     bulunduğu
    -0.06
    豊
    -0.06
     invalid
    -0.06
     BF
    -0.06
    nea
    -0.06
    locales
    -0.06
    hg
    -0.06
     Movies
    -0.06
    POSITIVE LOGITS
     PCR
    0.07
    (KeyCode
    0.06
     вой
    0.06
    Proj
    0.06
    优
    0.06
    _RATIO
    0.06
     граж
    0.06
     красив
    0.06
     gibt
    0.05
     petty
    0.05
    Activations Density 0.035%

    No Known Activations