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. 9857
    Prev
    Next
    INDEX
    Explanations

    the

    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
     poorly
    -0.06
    Debugger
    -0.06
     zus
    -0.06
     раньше
    -0.06
    cached
    -0.06
    ::↵
    -0.06
    \Helpers
    -0.06
     серьез
    -0.06
    toEqual
    -0.06
     каль
    -0.06
    POSITIVE LOGITS
    (GUI
    0.06
     hijos
    0.06
    States
    0.06
    母
    0.06
     age
    0.06
    (rel
    0.06
     LIMIT
    0.06
     mastering
    0.06
    .dst
    0.06
     grou
    0.06
    Activations Density 0.122%

    No Known Activations