© 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. 3-RESID-POST-AA
    11. 121736
    Prev
    Next
    INDEX
    Explanations

    Japanese/Chinese particles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    igne
    -0.06
     calculates
    -0.06
    níkem
    -0.06
    avorite
    -0.06
    	Id
    -0.06
    809
    -0.06
    ErrorException
    -0.06
    ijing
    -0.05
    inema
    -0.05
    обав
    -0.05
    POSITIVE LOGITS
    的
    0.11
     的
    0.09
    子的
    0.09
    의
    0.09
    たちの
    0.08
    スの
    0.08
     क
    0.08
    ルの
    0.07
    리의
    0.07
    のか
    0.07
    Activations Density 0.015%

    No Known Activations