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. 27-RESID-POST-AA
    6. 60883
    Prev
    Next
    INDEX
    Explanations

    Process description

    np_max-act-logits · gemini-2.0-flash
    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
    眠
    -0.07
    SimpleName
    -0.07
    (writer
    -0.07
     совсем
    -0.07
    екотор
    -0.07
    �
    -0.07
    /graphql
    -0.07
     
    -0.07
    	script
    -0.07
    Từ
    -0.07
    POSITIVE LOGITS
     inse
    0.08
    _PAY
    0.07
    Website
    0.06
    [#
    0.06
     admin
    0.06
    boro
    0.06
    Club
    0.06
    Autom
    0.06
     Documents
    0.06
     дом
    0.06
    Activations Density 0.120%

    No Known Activations