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. 7-RESID-POST-AA
    6. 5162
    Prev
    Next
    INDEX
    Explanations

    enumerated lists

    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
    erialization
    -0.07
    難
    -0.06
     hone
    -0.06
    inite
    -0.06
     आस
    -0.06
     Aus
    -0.06
     Ron
    -0.06
     torn
    -0.06
     Υ
    -0.06
    reation
    -0.06
    POSITIVE LOGITS
     العالمية
    0.06
    segments
    0.06
     Cleaner
    0.06
    SELECT
    0.06
    helpers
    0.06
    ्ट
    0.06
     horse
    0.06
    ій
    0.06
    Selectors
    0.05
    	Check
    0.05
    Activations Density 0.003%

    No Known Activations