© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 123907
    Prev
    Next
    INDEX
    Explanations

    voting or ratings

    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
    ssp
    -0.06
     freeze
    -0.06
     Mosque
    -0.06
    _Current
    -0.06
    Proto
    -0.06
     Through
    -0.06
     discomfort
    -0.06
     Sharia
    -0.06
     detectors
    -0.06
    &a
    -0.06
    POSITIVE LOGITS
    _Tis
    0.07
    heiten
    0.07
    ışık
    0.07
     гру
    0.06
     sophistication
    0.06
     عد
    0.06
     fact
    0.06
    dle
    0.06
     recep
    0.06
    	panel
    0.06
    Activations Density 0.011%

    No Known Activations