© 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. 8911
    Prev
    Next
    INDEX
    Explanations

    first person narratives

    np_max-act · gemini-2.0-flash

    The neuron fires on the Spanish self-reference phrase where the assistant sums up its own knowledge (“Eso es lo que sé sobre mí mismo”).

    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
    hung
    -0.06
    .List
    -0.06
     installations
    -0.06
     tours
    -0.06
     computations
    -0.06
    deck
    -0.06
     Suite
    -0.06
     cl
    -0.06
     seg
    -0.06
     Kerr
    -0.06
    POSITIVE LOGITS
    _SMALL
    0.08
    	TArray
    0.07
    :NSMakeRange
    0.07
    ниця
    0.07
     вст
    0.07
     สำ
    0.07
     появ
    0.07
     грун
    0.07
     भगव
    0.07
     LRV
    0.06
    Activations Density 0.051%

    No Known Activations