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. 23-RESID-POST-AA
    6. 40626
    Prev
    Next
    INDEX
    Explanations

    hex

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    baum
    -0.07
    ---------
    -0.07
    Danny
    -0.07
     conservatives
    -0.06
     Danny
    -0.06
     Brand
    -0.06
     estamos
    -0.06
     دارم
    -0.06
     votre
    -0.06
     Beijing
    -0.06
    POSITIVE LOGITS
    _HEX
    0.09
     hex
    0.07
     Developers
    0.07
     congen
    0.06
     updateTime
    0.06
    head
    0.06
     figsize
    0.06
     proceeding
    0.06
    โครงการ
    0.06
    (hex
    0.06
    Activations Density 0.004%

    No Known Activations