© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 73664
    Prev
    Next
    INDEX
    Explanations

    supervision

    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
     XII
    -0.07
     Cir
    -0.07
     initiate
    -0.07
    -cell
    -0.06
    Berlin
    -0.06
     Б
    -0.06
     prohibit
    -0.06
    	R
    -0.06
    ulated
    -0.06
     regulating
    -0.06
    POSITIVE LOGITS
    ，最
    0.07
    微笑
    0.07
     rave
    0.07
     içine
    0.07
     aftermath
    0.06
    vably
    0.06
     tc
    0.06
    ицин
    0.06
    .Cryptography
    0.06
    .Job
    0.06
    Activations Density 0.200%

    No Known Activations