© 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. 15-RESID-POST-AA
    11. 4593
    Prev
    Next
    INDEX
    Explanations

    permutations and sets

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dair
    -0.06
     CET
    -0.06
     Damon
    -0.06
     Handler
    -0.06
     Chaos
    -0.06
     müm
    -0.06
     Door
    -0.05
     Sight
    -0.05
     Bacon
    -0.05
     magnificent
    -0.05
    POSITIVE LOGITS
    entreprise
    0.07
     isEqualToString
    0.07
    aná
    0.07
    映画
    0.07
    盛
    0.06
    eced
    0.06
     karak
    0.06
    eventType
    0.06
    рон
    0.06
    solid
    0.06
    Activations Density 0.040%

    No Known Activations