© 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. 15-RESID-POST-AA
    11. 57375
    Prev
    Next
    INDEX
    Explanations

    answering questions

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     circuits
    -0.08
     planned
    -0.07
     collegiate
    -0.07
    udios
    -0.07
    rho
    -0.06
    .tasks
    -0.06
     paths
    -0.06
     shred
    -0.06
    _arc
    -0.06
     flashing
    -0.06
    POSITIVE LOGITS
    (folder
    0.07
    IllegalArgumentException
    0.06
    //
↵
↵
    0.06
    (view
    0.06
     vä
    0.06
    ��
    0.06
    .…↵↵
    0.06
    (intent
    0.06
     rowData
    0.06
    　　
    0.06
    Activations Density 0.033%

    No Known Activations