© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 25357
    Prev
    Next
    INDEX
    Explanations

    unwanted

    np_max-act · gemini-2.0-flash

    This neuron specifically activates on the word “unwanted.”

    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
     onCreateView
    -0.07
     листь
    -0.07
    .Connect
    -0.07
    .cpu
    -0.06
    .Debugf
    -0.06
    Hyper
    -0.06
    .Touch
    -0.06
    緊
    -0.06
    (Action
    -0.06
    isci
    -0.06
    POSITIVE LOGITS
     unwanted
    0.10
     undesirable
    0.08
     устра
    0.07
     undes
    0.07
    ات
    0.07
    gate
    0.07
     pests
    0.06
     OPT
    0.06
     Comment
    0.06
    шей
    0.06
    Activations Density 0.007%

    No Known Activations