© 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. 54439
    Prev
    Next
    INDEX
    Explanations

    death and violence

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of casualties (people killed, injured, left dead, etc.) in reports of violent events.

    oai_token-act-pair · o4-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
    Cou
    -0.08
    _statistics
    -0.07
     upwards
    -0.07
    を見
    -0.07
     harbour
    -0.07
     Bold
    -0.06
    mamak
    -0.06
     criteria
    -0.06
    ee
    -0.06
     Esk
    -0.06
    POSITIVE LOGITS
     roli
    0.07
    _LP
    0.06
    ukkan
    0.06
    ะแ
    0.06
    ------↵↵
    0.06
    Honda
    0.06
     absol
    0.06
    _PRIMARY
    0.06
    -shell
    0.06
    ्छ
    0.06
    Activations Density 0.022%

    No Known Activations