Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 129803
    Prev
    Next
    INDEX
    Explanations

    ibre

    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
     yarış
    -0.07
    Mat
    -0.06
     tk
    -0.06
    іту
    -0.06
     Matter
    -0.06
     ker
    -0.06
     вз
    -0.06
    .Inst
    -0.06
    composite
    -0.06
    Nİ
    -0.06
    POSITIVE LOGITS
     efficient
    0.07
    -efficient
    0.07
     possessing
    0.07
    ABSPATH
    0.06
     слаб
    0.06
     reduction
    0.06
    (userId
    0.06
     Дж
    0.06
    cipher
    0.06
     Charles
    0.06
    Activations Density 0.008%

    No Known Activations