© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 27-RESID-POST-AA
    11. 44872
    Prev
    Next
    INDEX
    Explanations

    AI safety refusals, particularly language used when declining to generate inappropriate or harmful content.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @grunklewordner
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Effects
    -0.07
     Americans
    -0.07
    git
    -0.07
    .proc
    -0.07
    项目
    -0.07
    !!}↵
    -0.06
    procs
    -0.06
     effects
    -0.06
     POLIT
    -0.06
    　　 　
    -0.06
    POSITIVE LOGITS
     alb
    0.07
     akin
    0.07
     relinqu
    0.06
     Pittsburgh
    0.06
    ลำ
    0.06
    siz
    0.06
     allev
    0.06
     &___
    0.06
     رق
    0.06
    ignty
    0.06
    Activations Density 0.084%

    No Known Activations