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. 10034
    Prev
    Next
    INDEX
    Explanations

    photo

    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
     por
    -0.08
     masks
    -0.07
    ังม
    -0.06
     UIScrollView
    -0.06
     commanded
    -0.06
     trout
    -0.06
     caves
    -0.06
    }`}↵
    -0.06
     Bird
    -0.06
    得
    -0.06
    POSITIVE LOGITS
     gözlem
    0.07
    ,current
    0.07
    즌
    0.06
     případně
    0.06
    ॉस
    0.06
    .proto
    0.06
    \_
    0.06
    �
    0.06
     arasındaki
    0.06
    ycastle
    0.06
    Activations Density 0.003%

    No Known Activations