© 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. 91499
    Prev
    Next
    INDEX
    Explanations

    Constants

    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
    734
    -0.07
     روح
    -0.07
    	rm
    -0.07
     कहन
    -0.07
     Suriye
    -0.07
     lille
    -0.06
    tanggal
    -0.06
    děl
    -0.06
    equiv
    -0.06
    .addTab
    -0.06
    POSITIVE LOGITS
     Matthews
    0.06
     tw
    0.06
    solution
    0.06
     офици
    0.06
     UIAlertController
    0.06
    เทศ
    0.06
     Ion
    0.06
    requested
    0.06
     Gret
    0.06
    ่าส
    0.06
    Activations Density 0.034%

    No Known Activations