© 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. 3-RESID-POST-AA
    11. 95371
    Prev
    Next
    INDEX
    Explanations

    proven

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .Res
    -0.06
     徒
    -0.06
    刘
    -0.06
    _school
    -0.06
    ِر
    -0.06
    �습니다
    -0.06
    _abstract
    -0.06
    (Roles
    -0.06
    worm
    -0.06
     userName
    -0.06
    POSITIVE LOGITS
     proven
    0.18
    ven
    0.10
     proved
    0.07
    
↵

↵
    0.07
    -tested
    0.07
     Applied
    0.07
    ΥΣ
    0.06
    Bien
    0.06
    เคร
    0.06
    -driven
    0.06
    Activations Density 0.002%

    No Known Activations