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. 19-RESID-POST-AA
    6. 83629
    Prev
    Next
    INDEX
    Explanations

    a

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mutable
    -0.06
    uccess
    -0.06
    Controls
    -0.06
     progressDialog
    -0.06
     IMDb
    -0.06
     harb
    -0.06
    ीदव
    -0.06
     segundo
    -0.06
     Agility
    -0.06
     comforts
    -0.06
    POSITIVE LOGITS
    (groupId
    0.07
     embod
    0.07
    ουλίου
    0.07
    _PWR
    0.07
    ้น
    0.07
    udy
    0.06
    ication
    0.06
     dislike
    0.06
    ristol
    0.06
     Lawn
    0.06
    Activations Density 0.060%

    No Known Activations