© 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. 124683
    Prev
    Next
    INDEX
    Explanations

    complex sentences

    np_max-act · gemini-2.0-flash

    The neuron activates on descriptive adjectives that convey cruelty, aggression, or dominance (e.g. “sadistic,” “relentless,” “dominant”).

    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
     bán
    -0.07
     Ireland
    -0.07
     scalability
    -0.06
     USED
    -0.06
    !");
    -0.06
    eated
    -0.06
    _trials
    -0.06
    444
    -0.06
     predicting
    -0.06
     Fallen
    -0.06
    POSITIVE LOGITS
     ngăn
    0.07
    ;i
    0.06
    (any
    0.06
     uns
    0.06
    スカ
    0.06
    larınız
    0.06
    	ss
    0.06
     terminating
    0.06
    (this
    0.06
    ‌س
    0.06
    Activations Density 0.147%

    No Known Activations