© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 7-RESID-POST-AA
    11. 95374
    Prev
    Next
    INDEX
    Explanations

    crime reports

    np_max-act · gemini-2.0-flash

    news-style descriptions of violent criminal incidents and law-enforcement responses, particularly shootings or stabbings with suspects, victims, and timestamps.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OSP
    -0.07
     Mon
    -0.07
    Sym
    -0.06
    urred
    -0.06
    (li
    -0.06
    _soup
    -0.06
    胎
    -0.06
    aro
    -0.06
    ORM
    -0.06
    norm
    -0.06
    POSITIVE LOGITS
     dök
    0.07
     โรงเร
    0.06
    checkbox
    0.06
    Logic
    0.06
     Vanilla
    0.06
     Exclude
    0.06
    currentState
    0.06
     trays
    0.06
     federally
    0.06
     referencing
    0.06
    Activations Density 0.228%

    No Known Activations