© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 90939
    Prev
    Next
    INDEX
    Explanations

    day

    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
    �情
    -0.06
    iments
    -0.06
    317
    -0.06
     是否
    -0.06
     روست
    -0.06
    EEDED
    -0.06
     zaten
    -0.06
    겨
    -0.06
    styleType
    -0.05
     palette
    -0.05
    POSITIVE LOGITS
    <Task
    0.07
    	win
    0.07
    asting
    0.07
     accommodations
    0.07
     conservative
    0.06
    vider
    0.06
     damage
    0.06
    없음
    0.06
     abbreviation
    0.06
    icot
    0.06
    Activations Density 0.032%

    No Known Activations