© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 79426
    Prev
    Next
    INDEX
    Explanations

    judge/justice

    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
    ूं
    -0.06
    .VERSION
    -0.06
     rollers
    -0.06
    また
    -0.06
    asket
    -0.06
    _REDIRECT
    -0.06
    Besides
    -0.06
     Omar
    -0.06
    ォ
    -0.06
     دی
    -0.06
    POSITIVE LOGITS
    /from
    0.07
    }@
    0.06
     Alo
    0.06
    uple
    0.06
    getInstance
    0.06
    Naming
    0.06
     dịch
    0.06
     Tale
    0.06
    위
    0.06
     جن
    0.06
    Activations Density 0.004%

    No Known Activations