Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 127728
    Prev
    Next
    INDEX
    Explanations

    kill

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     entrance
    -0.08
     Από
    -0.08
     posi
    -0.07
    (cond
    -0.07
    ((((
    -0.07
             
    -0.06
    uchos
    -0.06
    .).
    -0.06
    arda
    -0.06
    ardu
    -0.06
    POSITIVE LOGITS
     kill
    0.11
     Kill
    0.09
     kills
    0.09
     killing
    0.08
     slaughter
    0.08
    .kill
    0.08
    杀
    0.07
     BMI
    0.07
     torture
    0.07
    ill
    0.07
    Activations Density 0.015%

    No Known Activations