© 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. 11-RESID-POST-AA
    11. 123257
    Prev
    Next
    INDEX
    Explanations

    werden

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فران
    -0.08
     apprentices
    -0.06
     annunci
    -0.06
    Abort
    -0.06
     às
    -0.06
    bot
    -0.06
    chant
    -0.06
     Sly
    -0.06
     Chair
    -0.06
     مثال
    -0.06
    POSITIVE LOGITS
     werden
    0.10
     wird
    0.10
     werd
    0.09
     wurde
    0.09
     wordt
    0.08
    된
    0.08
    になった
    0.08
    eração
    0.08
    -generation
    0.07
     を
    0.07
    Activations Density 0.018%

    No Known Activations