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. 30414
    Prev
    Next
    INDEX
    Explanations

    of

    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
    似乎
    -0.07
    лами
    -0.07
    mas
    -0.06
     emblem
    -0.06
    'en
    -0.06
     тоді
    -0.06
    	all
    -0.06
    	names
    -0.06
     confirms
    -0.06
    弱
    -0.06
    POSITIVE LOGITS
    asyarak
    0.06
    ruitment
    0.06
    这样的
    0.06
    announcement
    0.06
    ційної
    0.06
    |M
    0.06
     productions
    0.06
     CH
    0.06
    .readInt
    0.06
     reason
    0.06
    Activations Density 0.009%

    No Known Activations