© 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. 15-RESID-POST-AA
    6. 113622
    Prev
    Next
    INDEX
    Explanations

    on

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rudd
    -0.07
    _collision
    -0.07
     SYSTEM
    -0.07
     Cuomo
    -0.07
    διά
    -0.07
     McGill
    -0.07
     glide
    -0.07
     scrape
    -0.07
    651
    -0.07
     dir
    -0.06
    POSITIVE LOGITS
     appendix
    0.06
    فات
    0.06
     AttributeError
    0.06
    	Dictionary
    0.06
    (cl
    0.06
     سان
    0.06
    زل
    0.06
    _ATTACK
    0.06
     ưu
    0.06
    Closed
    0.05
    Activations Density 0.006%

    No Known Activations