© 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
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 28172
    Prev
    Next
    INDEX
    Explanations

    V

    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
    کو
    -0.07
     cultura
    -0.07
     replaced
    -0.06
    Clark
    -0.06
     νο
    -0.06
     chỗ
    -0.06
     charakter
    -0.06
    .tests
    -0.06
     surfaced
    -0.06
     Impress
    -0.06
    POSITIVE LOGITS
    有什么
    0.07
    (Response
    0.07
    .Payload
    0.07
    zelf
    0.06
    (Sprite
    0.06
    обра�
    0.06
    (Session
    0.06
    xed
    0.06
    <C
    0.06
    _IB
    0.06
    Activations Density 0.061%

    No Known Activations