© 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. 7-RESID-POST-AA
    11. 25033
    Prev
    Next
    INDEX
    Explanations

    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
    际
    -0.06
    Anal
    -0.06
    .Verify
    -0.06
    .warning
    -0.06
    ца
    -0.06
     Produce
    -0.06
    ์ใน
    -0.06
     sche
    -0.06
    arded
    -0.06
    цу
    -0.06
    POSITIVE LOGITS
     vetor
    0.06
    .getInfo
    0.06
    藤
    0.06
     полностью
    0.06
     james
    0.06
     questo
    0.06
    ่งชาต
    0.06
     Griffith
    0.06
     드라마
    0.06
     protects
    0.06
    Activations Density 0.092%

    No Known Activations