© 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. 11-RESID-POST-AA
    11. 52308
    Prev
    Next
    INDEX
    Explanations

    for

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itt
    -0.06
    ej
    -0.06
    jsx
    -0.06
     lượng
    -0.06
     Αθή
    -0.06
    228
    -0.06
    ी.
    -0.06
    acy
    -0.06
     podporu
    -0.06
     guide
    -0.06
    POSITIVE LOGITS
    /sm
    0.07
    bert
    0.06
     quần
    0.06
     sham
    0.06
     희
    0.06
     Ky
    0.06
     unknow
    0.06
    oldur
    0.06
    ποι
    0.06
    -il
    0.06
    Activations Density 0.227%

    No Known Activations