© 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. 30001
    Prev
    Next
    INDEX
    Explanations

    for

    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
     Lag
    -0.07
    	URL
    -0.07
     lovers
    -0.06
    $temp
    -0.06
    	catch
    -0.06
     Trials
    -0.06
     LOGGER
    -0.06
    .time
    -0.06
     Wenn
    -0.06
    .factory
    -0.06
    POSITIVE LOGITS
     是否
    0.07
    AssignableFrom
    0.07
    ZE
    0.07
    ør
    0.07
    ---------------↵
    0.07
    _ascii
    0.06
     ל
    0.06
    ère
    0.06
    ้ง
    0.06
    \Api
    0.06
    Activations Density 0.039%

    No Known Activations