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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 44386
    Prev
    Next
    INDEX
    Explanations

    wrongdoing

    np_max-act · gemini-2.0-flash

    This neuron detects phrases expressing moral blame or wrongdoing (e.g. “done something wrong,” “bad things happen to bad people,” “cause of their present suffering”).

    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
    574
    -0.06
     trends
    -0.06
    <data
    -0.06
    13
    -0.06
     affordable
    -0.06
     latina
    -0.06
     digestive
    -0.06
    ци
    -0.06
    Dog
    -0.06
     Applicants
    -0.06
    POSITIVE LOGITS
     sebeb
    0.07
    .createServer
    0.07
    &view
    0.07
    eps
    0.07
     caching
    0.07
     {})
    0.06
     invoke
    0.06
    BSD
    0.06
    Boot
    0.06
     lashes
    0.06
    Activations Density 0.046%

    No Known Activations