© 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. 7-RESID-POST-AA
    11. 29894
    Prev
    Next
    INDEX
    Explanations

    temper

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     grey
    -0.07
     наг
    -0.07
    classic
    -0.07
     gray
    -0.06
    ayla
    -0.06
     rosa
    -0.06
    SELF
    -0.06
     Lynn
    -0.06
     nye
    -0.06
     BLACK
    -0.06
    POSITIVE LOGITS
     temper
    0.15
     Temper
    0.13
     Tem
    0.12
    Tem
    0.11
     tem
    0.10
     tempered
    0.09
     TEM
    0.09
     temperament
    0.09
    .tem
    0.08
    per
    0.08
    Activations Density 0.007%

    No Known Activations