© 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
    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. 78457
    Prev
    Next
    INDEX
    Explanations

    Cathedral

    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
     труд
    -0.07
    -mode
    -0.07
    workers
    -0.06
     Horse
    -0.06
    Zero
    -0.06
     hops
    -0.06
    )['
    -0.06
     mondo
    -0.06
     gió
    -0.06
     Ones
    -0.06
    POSITIVE LOGITS
     Cathedral
    0.20
     cathedral
    0.17
    edral
    0.08
     Abbey
    0.08
     VLC
    0.07
    epy
    0.07
     entirety
    0.07
     abb
    0.07
     Basil
    0.07
     CST
    0.07
    Activations Density 0.003%

    No Known Activations