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. 40686
    Prev
    Next
    INDEX
    Explanations

    plastic

    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
     sotto
    -0.06
     breed
    -0.06
     donner
    -0.06
     differential
    -0.06
     empir
    -0.06
    death
    -0.06
     tend
    -0.06
     warning
    -0.06
     tran
    -0.06
     distributions
    -0.06
    POSITIVE LOGITS
    Ultimately
    0.07
    PLAY
    0.07
     فت
    0.06
    Peak
    0.06
    سن
    0.06
    �乐
    0.06
    ocolate
    0.06
    .host
    0.06
    play
    0.06
    STANCE
    0.06
    Activations Density 0.002%

    No Known Activations