© 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. 7-RESID-POST-AA
    11. 4932
    Prev
    Next
    INDEX
    Explanations

    regular expressions/code

    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
     درآمد
    -0.07
    WND
    -0.06
    一次
    -0.06
     circus
    -0.06
     )(
    -0.06
    ρούν
    -0.06
     panoramic
    -0.05
    521
    -0.05
    اكن
    -0.05
     Gand
    -0.05
    POSITIVE LOGITS
    today
    0.07
     fieldType
    0.07
    ��
    0.06
     nanoparticles
    0.06
     sparks
    0.06
     μέσα
    0.06
    asy
    0.06
    _put
    0.06
    _detected
    0.06
     Verm
    0.06
    Activations Density 0.005%

    No Known Activations