© 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. 123178
    Prev
    Next
    INDEX
    Explanations

    Racing mind

    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
     maj
    -0.06
     듯
    -0.06
    	   ↵
    -0.06
     pe
    -0.06
     pied
    -0.06
     pang
    -0.06
     největší
    -0.06
     studied
    -0.06
     plateau
    -0.06
    FINE
    -0.06
    POSITIVE LOGITS
     initialize
    0.07
    .Event
    0.06
    层
    0.06
    .Transport
    0.06
    .Rotate
    0.06
     Benchmark
    0.06
    二十
    0.06
    owel
    0.06
     Allen
    0.06
    .util
    0.06
    Activations Density 0.032%

    No Known Activations