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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 85695
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    何か
    -0.06
     so
    -0.06
    iance
    -0.06
    So
    -0.06
     Polo
    -0.06
     mesma
    -0.06
    Encrypt
    -0.06
    多
    -0.06
     general
    -0.06
     First
    -0.06
    POSITIVE LOGITS
     INS
    0.07
     конструкции
    0.07
    .persistent
    0.06
    .executeUpdate
    0.06
     distract
    0.06
     <-
    0.06
     Undefined
    0.06
     transitional
    0.06
     Rach
    0.06
     revolution
    0.06
    Activations Density 0.005%

    No Known Activations