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. 10374
    Prev
    Next
    INDEX
    Explanations

    Large structures and cities

    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
    (can
    -0.07
    abstract
    -0.07
     اروپ
    -0.07
     دقی
    -0.07
    тери
    -0.07
    하지만
    -0.07
     Pie
    -0.06
     sû
    -0.06
    bean
    -0.06
    _Abstract
    -0.06
    POSITIVE LOGITS
     minY
    0.07
     Bollywood
    0.06
    inks
    0.06
    ismet
    0.06
     Αγ
    0.06
     motto
    0.06
     inner
    0.06
    γ
    0.05
    Interop
    0.05
    gp
    0.05
    Activations Density 0.041%

    No Known Activations