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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 15-RESID-POST-AA
    6. 40563
    Prev
    Next
    INDEX
    Explanations

    abuse and torture

    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
     CIA
    -0.07
     терап
    -0.06
    알
    -0.06
     알
    -0.06
     sóc
    -0.06
    -Ф
    -0.06
    .Surface
    -0.06
     야
    -0.06
    ५
    -0.06
     Bath
    -0.06
    POSITIVE LOGITS
    (Connection
    0.07
    -work
    0.07
     ListView
    0.06
    born
    0.06
     Gambling
    0.06
    essions
    0.06
     Если
    0.06
    ensor
    0.06
    mons
    0.06
    _FB
    0.06
    Activations Density 0.012%

    No Known Activations