© 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. 55523
    Prev
    Next
    INDEX
    Explanations

    geographical locations

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is detect cardinal direction words (e.g. north, south, east, west) in geographic descriptions.

    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
     Physics
    -0.07
    plates
    -0.07
     خودش
    -0.06
    前に
    -0.06
     Books
    -0.06
     Oven
    -0.06
    paper
    -0.06
    -0.06
    _choose
    -0.06
    　　　　　　　　　　
    -0.06
    POSITIVE LOGITS
    settings
    0.06
     CTL
    0.06
     黑
    0.06
     geral
    0.06
     rio
    0.06
    _cpus
    0.05
     rental
    0.05
     aut
    0.05
     �
    0.05
     MonoBehaviour
    0.05
    Activations Density 0.006%

    No Known Activations