© 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. 6877
    Prev
    Next
    INDEX
    Explanations

    Radar

    np_max-act · gemini-2.0-flash

    The neuron selectively fires on the repeated “On Our Radar” (and similar section‐header) phrases, i.e. it detects that editorial header.

    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
     пом
    -0.08
     ridicule
    -0.07
     Imp
    -0.07
    doctrine
    -0.06
    quets
    -0.06
    eut
    -0.06
     говор
    -0.06
     Supports
    -0.06
    .design
    -0.06
     exiting
    -0.06
    POSITIVE LOGITS
     ομά
    0.08
    .batch
    0.07
    Using
    0.06
     میک
    0.06
     China
    0.06
     republika
    0.06
     Agent
    0.06
     Conscious
    0.06
     coraz
    0.06
    ای
    0.06
    Activations Density 0.000%

    No Known Activations