© 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 (Instruct)
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 111690
    Prev
    Next
    INDEX
    Explanations

    non-English language

    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
    ，因
    -0.07
    Printer
    -0.06
     краї
    -0.06
    いている
    -0.06
     Launch
    -0.06
    ardır
    -0.06
     Sends
    -0.06
    cth
    -0.06
    Các
    -0.06
     IllegalArgumentException
    -0.06
    POSITIVE LOGITS
     stumble
    0.07
    /false
    0.07
     Slav
    0.07
    .uri
    0.06
     Buddhism
    0.06
     needed
    0.06
     Buddhist
    0.06
     improvements
    0.06
    入り
    0.06
     curled
    0.06
    Activations Density 0.048%

    No Known Activations