© 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. 19-RESID-POST-AA
    11. 91766
    Prev
    Next
    INDEX
    Explanations

    actions and instructions

    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
    .poster
    -0.07
    ्�
    -0.06
     {}'.
    -0.06
    ’t
    -0.06
     Bạn
    -0.06
     (*)
    -0.06
     Dems
    -0.06
     виробництва
    -0.06
    _u
    -0.06
    。我
    -0.06
    POSITIVE LOGITS
     Phong
    0.06
     코
    0.06
     yasak
    0.06
     Lemon
    0.06
     cg
    0.06
     라이
    0.06
     liable
    0.06
     visualize
    0.06
     kay
    0.06
     вог
    0.06
    Activations Density 0.051%

    No Known Activations