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. 11-RESID-POST-AA
    6. 101110
    Prev
    Next
    INDEX
    Explanations

    Going somewhere

    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
     incorporate
    -0.07
    än
    -0.07
     awakening
    -0.07
     compatibility
    -0.07
     Feed
    -0.07
    (annotation
    -0.07
     Entity
    -0.06
     Ihnen
    -0.06
    pp
    -0.06
    solid
    -0.06
    POSITIVE LOGITS
     improper
    0.07
     дотрим
    0.07
    	writel
    0.06
     contag
    0.06
    quet
    0.06
     وزار
    0.06
    _COM
    0.06
    $l
    0.06
    llum
    0.06
     TSRMLS
    0.06
    Activations Density 0.035%

    No Known Activations