© 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 (Instruct)
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 9203
    Prev
    Next
    INDEX
    Explanations

    hygiene and masks

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     апреля
    -0.07
    .Stretch
    -0.07
    除了
    -0.07
     koy
    -0.06
     препара
    -0.06
    /ap
    -0.06
     실제
    -0.06
     пер
    -0.06
    ])));↵
    -0.06
     kode
    -0.06
    POSITIVE LOGITS
    %.
    0.06
    utherford
    0.06
     vál
    0.06
     Richt
    0.06
     System
    0.06
     Flor
    0.06
    <usize
    0.06
     installation
    0.06
    /config
    0.06
     system
    0.06
    Activations Density 0.030%

    No Known Activations