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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 78292
    Prev
    Next
    INDEX
    Explanations

    aerial

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _builder
    -0.07
    (epoch
    -0.07
    _override
    -0.06
     burden
    -0.06
    	lock
    -0.06
    Defaults
    -0.06
     modify
    -0.06
     broadcasting
    -0.06
    (value
    -0.06
    Ok
    -0.06
    POSITIVE LOGITS
     aerial
    0.14
    erial
    0.09
     مایل
    0.09
     Arial
    0.08
     Ariel
    0.08
     uç
    0.07
    Arial
    0.07
    幹
    0.07
     Flying
    0.07
     DataGridView
    0.07
    Activations Density 0.002%

    No Known Activations