© 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. 11-RESID-POST-AA
    11. 25846
    Prev
    Next
    INDEX
    Explanations

    mal

    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_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
     flora
    -0.07
     trout
    -0.07
     Remed
    -0.07
     pleasant
    -0.06
    _rotation
    -0.06
    usp
    -0.06
    ysics
    -0.06
    едак
    -0.06
    附
    -0.06
     German
    -0.06
    POSITIVE LOGITS
    fd
    0.06
    realloc
    0.06
    Tracker
    0.06
    IfNeeded
    0.06
    permalink
    0.06
    collector
    0.06
     anonymously
    0.06
    toBeDefined
    0.06
    lanır
    0.06
    _INC
    0.06
    Activations Density 0.219%

    No Known Activations