© 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. 35155
    Prev
    Next
    INDEX
    Explanations

    or and

    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
    ű
    -0.07
     Laundry
    -0.07
     Fritz
    -0.06
    -color
    -0.06
    430
    -0.06
     lab
    -0.06
    xor
    -0.06
    라이
    -0.06
     arrives
    -0.06
    錢
    -0.06
    POSITIVE LOGITS
    /qt
    0.07
     yielding
    0.07
    _CHOICES
    0.07
    (skill
    0.07
    	StringBuffer
    0.06
     diversion
    0.06
    궁
    0.06
    _EC
    0.06
    ,$
    0.06
     وان
    0.06
    Activations Density 0.026%

    No Known Activations