© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8703
    Prev
    Next
    INDEX
    Explanations

    erase

    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
     competency
    -0.07
    nitř
    -0.06
     reperc
    -0.06
    を見
    -0.06
     RESPONS
    -0.06
     responsibility
    -0.06
    етерб
    -0.06
    _TRUE
    -0.06
    dims
    -0.06
     CONNECT
    -0.06
    POSITIVE LOGITS
     long
    0.07
    exe
    0.06
     evacuate
    0.06
    atore
    0.06
     Tenant
    0.06
    earable
    0.06
    ışma
    0.06
    _failed
    0.06
    (cls
    0.06
     FC
    0.06
    Activations Density 0.007%

    No Known Activations