© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 109236
    Prev
    Next
    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    This neuron activates on the sequence “order to trick,” i.e. phrasing that describes an instruction’s goal of deceiving someone.

    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
    116
    -0.07
    _unsigned
    -0.06
    693
    -0.06
    fort
    -0.06
    .putText
    -0.06
    EMON
    -0.06
    -with
    -0.06
     companions
    -0.06
    挂
    -0.06
    .launch
    -0.06
    POSITIVE LOGITS
     interv
    0.07
     Vector
    0.06
     femin
    0.06
    .innerWidth
    0.06
     masih
    0.06
    .arguments
    0.06
     ¬
    0.06
     succès
    0.06
     rhetorical
    0.06
    cház
    0.06
    Activations Density 0.024%

    No Known Activations