© 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 (Instruct)
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 121768
    Prev
    Next
    INDEX
    Explanations

    Tom

    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
    ubat
    -0.07
    reated
    -0.06
    pegawai
    -0.06
     рад
    -0.06
     Kemp
    -0.06
    adele
    -0.06
     contraction
    -0.06
     Needle
    -0.06
    laş
    -0.05
     bridal
    -0.05
    POSITIVE LOGITS
     Tom
    0.39
    Tom
    0.33
     TOM
    0.22
     tom
    0.19
    tom
    0.16
     Tommy
    0.14
    .tom
    0.13
     توم
    0.09
     Том
    0.09
     Thom
    0.09
    Activations Density 0.007%

    No Known Activations