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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 15-RESID-POST-AA
    6. 127895
    Prev
    Next
    INDEX
    Explanations

    real

    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
     Kut
    -0.07
    ườn
    -0.06
    ğitim
    -0.06
    	Run
    -0.06
    �ん
    -0.06
    landa
    -0.06
    (".",
    -0.06
    ebin
    -0.06
    openh
    -0.06
    voor
    -0.06
    POSITIVE LOGITS
    طلق
    0.07
    _good
    0.07
     类
    0.07
     jasmine
    0.06
    keypress
    0.06
     kick
    0.06
    =explode
    0.06
    �
    0.06
    .getString
    0.06
    ﻴ
    0.06
    Activations Density 0.007%

    No Known Activations