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. 30300
    Prev
    Next
    INDEX
    Explanations

    Text excerpts

    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
    -opt
    -0.06
     �
    -0.06
    JSON
    -0.06
     inherits
    -0.06
    restriction
    -0.06
    	sub
    -0.06
     broadly
    -0.06
    苏
    -0.06
     cupid
    -0.06
    $img
    -0.06
    POSITIVE LOGITS
     halted
    0.07
     انواع
    0.07
    815
    0.06
    روش
    0.06
     MLS
    0.06
     Jakarta
    0.06
     вет
    0.06
     içine
    0.06
    олуч
    0.06
     belum
    0.06
    Activations Density 0.000%

    No Known Activations