Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 99559
    Prev
    Next
    INDEX
    Explanations

    data privacy

    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
     clipped
    -0.07
     Bonus
    -0.07
    ytut
    -0.06
     cr
    -0.06
    oupon
    -0.06
    abinet
    -0.06
            ↵↵
    -0.06
    aro
    -0.06
     tasted
    -0.06
     posture
    -0.06
    POSITIVE LOGITS
    .getElementsByTagName
    0.07
    =count
    0.07
     disag
    0.07
     alertController
    0.07
    []):
    0.06
     exter
    0.06
    	FILE
    0.06
    *)&
    0.06
     toItem
    0.06
     edt
    0.06
    Activations Density 0.011%

    No Known Activations